Applied Sciences

Editorial

Jump to: Research, Review

4 pages, 162 KiB

Open AccessEditorial

Special Issue on “Advances in Image Processing, Analysis and Recognition Technology”

by Dariusz Frejlichowski

Appl. Sci. 2020, 10(21), 7582; https://doi.org/10.3390/app10217582 - 28 Oct 2020

Cited by 1 | Viewed by 1498

Abstract

For many decades researchers have been trying to make computer analysis of images as effective as the human vision system is [...] Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

Research

Jump to: Editorial, Review

12 pages, 384 KiB

Open AccessArticle

The Analysis of Shape Features for the Purpose of Exercise Types Classification Using Silhouette Sequences

by Katarzyna Gościewska and Dariusz Frejlichowski

Appl. Sci. 2020, 10(19), 6728; https://doi.org/10.3390/app10196728 - 25 Sep 2020

Cited by 5 | Viewed by 2315

Abstract

This paper presents the idea of using simple shape features for action recognition based on binary silhouettes. Shape features are analysed as they change over time within an action sequence. It is shown that basic shape characteristics can discriminate between short, primitive actions [...] Read more.

This paper presents the idea of using simple shape features for action recognition based on binary silhouettes. Shape features are analysed as they change over time within an action sequence. It is shown that basic shape characteristics can discriminate between short, primitive actions performed by a single person. The proposed approach is tested on the Weizmann database using a various number of classes. Binary foreground masks (silhouettes) are replaced with convex hulls, which highlights some shape characteristics. Centroid locations are combined with some other simple shape descriptors. Each action sequence is represented using a vector with shape features and Discrete Fourier Transform. Classification is based on leave-one-sequence-out approach and employs Euclidean distance, correlation coefficient or C1 correlation. A list of processing steps for action recognition is explained and followed by some experiments that yielded accuracy exceeding 90%. The idea behind the presented approach is to develop a solution for action recognition that could be applied in a kind of human activity recognition system associated with the Ambient Assisted Living concept, helping adults increasing their activity levels by monitoring them during exercises. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

17 pages, 12036 KiB

Open AccessArticle

Advances in Optical Image Analysis Textural Segmentation in Ironmaking

by Eugene Donskoi and Andrei Poliakov

Appl. Sci. 2020, 10(18), 6242; https://doi.org/10.3390/app10186242 - 8 Sep 2020

Cited by 7 | Viewed by 2962

Abstract

Optical image analysis is commonly used to characterize different feedstock material for ironmaking, such as iron ore, iron ore sinter, coal and coke. Information is often needed for phases which have the same reflectivity and chemical composition, but different morphology. Such information is [...] Read more.

Optical image analysis is commonly used to characterize different feedstock material for ironmaking, such as iron ore, iron ore sinter, coal and coke. Information is often needed for phases which have the same reflectivity and chemical composition, but different morphology. Such information is usually obtained by manual point counting, which is quite expensive and may not provide consistent results between different petrologists. To perform accurate segmentation of such phases using automated optical image analysis, the software must be able to identify specific textures. CSIRO’s Carbon Steel Futures group has developed an optical image analysis software package called Mineral4/Recognition4, which incorporates a dedicated textural identification module allowing segmentation of such phases. The article discusses the problems associated with segmentation of similar phases in different ironmaking feedstock material using automated optical image analysis and demonstrates successful algorithms for textural identification. The examples cover segmentation of three different coke phases: two types of Inert Maceral Derived Components (IMDC), non-reacted and partially reacted, and Reacted Maceral Derived Components (RMDC); primary and secondary hematite in iron ore sinter; and minerals difficult to distinguish with traditional thresholding in iron ore. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

15 pages, 22902 KiB

Open AccessArticle

Object Detection Using Multi-Scale Balanced Sampling

by Hang Yu, Jiulu Gong and Derong Chen

Appl. Sci. 2020, 10(17), 6053; https://doi.org/10.3390/app10176053 - 1 Sep 2020

Cited by 5 | Viewed by 2617

Abstract

Detecting small objects and objects with large scale variants are always challenging for deep learning based object detection approaches. Many efforts have been made to solve these problems such as adopting more effective network structures, image features, loss functions, etc. However, for both [...] Read more.

Detecting small objects and objects with large scale variants are always challenging for deep learning based object detection approaches. Many efforts have been made to solve these problems such as adopting more effective network structures, image features, loss functions, etc. However, for both small objects detection and detecting objects with various scale in single image, the first thing should be solve is the matching mechanism between anchor boxes and ground-truths. In this paper, an approach based on multi-scale balanced sampling(MB-RPN) is proposed for the difficult matching of small objects and detecting multi-scale objects. According to the scale of the anchor boxes, different positive and negative sample IOU discriminate thresholds are adopted to improve the probability of matching the small object area with the anchor boxes so that more small object samples are included in the training process. Moreover, the balanced sampling method is proposed for the collected samples, the samples are further divided and uniform sampling to ensure the diversity of samples in training process. Several datasets are adopted to evaluate the MB-RPN, the experimental results show that compare with the similar approach, MB-RPN improves detection performances effectively. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

9 pages, 1567 KiB

Open AccessArticle

Hybrid-Attention Network for RGB-D Salient Object Detection

by Yuzhen Chen and Wujie Zhou

Appl. Sci. 2020, 10(17), 5806; https://doi.org/10.3390/app10175806 - 21 Aug 2020

Cited by 11 | Viewed by 2436

Abstract

Depth information has been widely used to improve RGB-D salient object detection by extracting attention maps to determine the position information of objects in an image. However, non-salient objects may be close to the depth sensor and present high pixel intensities in the [...] Read more.

Depth information has been widely used to improve RGB-D salient object detection by extracting attention maps to determine the position information of objects in an image. However, non-salient objects may be close to the depth sensor and present high pixel intensities in the depth maps. This situation in depth maps inevitably leads to erroneously emphasize non-salient areas and may have a negative impact on the saliency results. To mitigate this problem, we propose a hybrid attention neural network that fuses middle- and high-level RGB features with depth features to generate a hybrid attention map to remove background information. The proposed network extracts multilevel features from RGB images using the Res2Net architecture and then integrates high-level features from depth maps using the Inception-v4-ResNet2 architecture. The mixed high-level RGB features and depth features generate the hybrid attention map, which is then multiplied to the low-level RGB features. After decoding by several convolutions and upsampling, we obtain the final saliency prediction, achieving state-of-the-art performance on the NJUD and NLPR datasets. Moreover, the proposed network has good generalization ability compared with other methods. An ablation study demonstrates that the proposed network effectively performs saliency prediction even when non-salient objects interfere detection. In fact, after removing the branch with high-level RGB features, the RGB attention map that guides the network for saliency prediction is lost, and all the performance measures decline. The resulting prediction map from the ablation study shows the effect of non-salient objects close to the depth sensor. This effect is not present when using the complete hybrid attention network. Therefore, RGB information can correct and supplement depth information, and the corresponding hybrid attention map is more robust than using a conventional attention map constructed only with depth information. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

25 pages, 2179 KiB

Open AccessArticle

Aerial Scene Classification through Fine-Tuning with Adaptive Learning Rates and Label Smoothing

by Biserka Petrovska, Tatjana Atanasova-Pacemska, Roberto Corizzo, Paolo Mignone, Petre Lameski and Eftim Zdravevski

Appl. Sci. 2020, 10(17), 5792; https://doi.org/10.3390/app10175792 - 21 Aug 2020

Cited by 35 | Viewed by 4036

Abstract

Remote Sensing (RS) image classification has recently attracted great attention for its application in different tasks, including environmental monitoring, battlefield surveillance, and geospatial object detection. The best practices for these tasks often involve transfer learning from pre-trained Convolutional Neural Networks (CNNs). A common [...] Read more.

Remote Sensing (RS) image classification has recently attracted great attention for its application in different tasks, including environmental monitoring, battlefield surveillance, and geospatial object detection. The best practices for these tasks often involve transfer learning from pre-trained Convolutional Neural Networks (CNNs). A common approach in the literature is employing CNNs for feature extraction, and subsequently train classifiers exploiting such features. In this paper, we propose the adoption of transfer learning by fine-tuning pre-trained CNNs for end-to-end aerial image classification. Our approach performs feature extraction from the fine-tuned neural networks and remote sensing image classification with a Support Vector Machine (SVM) model with linear and Radial Basis Function (RBF) kernels. To tune the learning rate hyperparameter, we employ a linear decay learning rate scheduler as well as cyclical learning rates. Moreover, in order to mitigate the overfitting problem of pre-trained models, we apply label smoothing regularization. For the fine-tuning and feature extraction process, we adopt the Inception-v3 and Xception inception-based CNNs, as well the residual-based networks ResNet50 and DenseNet121. We present extensive experiments on two real-world remote sensing image datasets: AID and NWPU-RESISC45. The results show that the proposed method exhibits classification accuracy of up to 98%, outperforming other state-of-the-art methods. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

20 pages, 4403 KiB

Open AccessArticle

Pansharpening by Complementing Compressed Sensing with Spectral Correction

by Naoko Tsukamoto, Yoshihiro Sugaya and Shinichiro Omachi

Appl. Sci. 2020, 10(17), 5789; https://doi.org/10.3390/app10175789 - 21 Aug 2020

Cited by 2 | Viewed by 1907

Abstract

Pansharpening (PS) is a process used to generate high-resolution multispectral (MS) images from high-spatial-resolution panchromatic (PAN) and high-spectral-resolution multispectral images. In this paper, we propose a method for pansharpening by focusing on a compressed sensing (CS) technique. The spectral reproducibility of the CS [...] Read more.

Pansharpening (PS) is a process used to generate high-resolution multispectral (MS) images from high-spatial-resolution panchromatic (PAN) and high-spectral-resolution multispectral images. In this paper, we propose a method for pansharpening by focusing on a compressed sensing (CS) technique. The spectral reproducibility of the CS technique is high due to its image reproducibility, but the reproduced image is blurry. Although methods of complementing this incomplete reproduction have been proposed, it is known that the existing method may cause ringing artifacts. On the other hand, component substitution is another technique used for pansharpening. It is expected that the spatial resolution of the images generated by this technique will be as high as that of the high-resolution PAN image, because the technique uses the corrected intensity calculated from the PAN image. Based on these facts, the proposed method fuses the intensity obtained by the component substitution method and the intensity obtained by the CS technique to move the spatial resolution of the reproduced image close to that of the PAN image while reducing the spectral distortion. Experimental results showed that the proposed method can reduce spectral distortion and maintain spatial resolution better than the existing methods. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

16 pages, 3415 KiB

Open AccessArticle

Automatic CNN-Based Arabic Numeral Spotting and Handwritten Digit Recognition by Using Deep Transfer Learning in Ottoman Population Registers

by Yekta Said Can and M. Erdem Kabadayı

Appl. Sci. 2020, 10(16), 5430; https://doi.org/10.3390/app10165430 - 6 Aug 2020

Cited by 16 | Viewed by 4130

Abstract

Historical manuscripts and archival documentation are handwritten texts which are the backbone sources for historical inquiry. Recent developments in the digital humanities field and the need for extracting information from the historical documents have fastened the digitization processes. Cutting edge machine learning methods [...] Read more.

Historical manuscripts and archival documentation are handwritten texts which are the backbone sources for historical inquiry. Recent developments in the digital humanities field and the need for extracting information from the historical documents have fastened the digitization processes. Cutting edge machine learning methods are applied to extract meaning from these documents. Page segmentation (layout analysis), keyword, number and symbol spotting, handwritten text recognition algorithms are tested on historical documents. For most of the languages, these techniques are widely studied and high performance techniques are developed. However, the properties of Arabic scripts (i.e., diacritics, varying script styles, diacritics, and ligatures) create additional problems for these algorithms and, therefore, the number of research is limited. In this research, we first automatically spotted the Arabic numerals from the very first series of population registers of the Ottoman Empire conducted in the mid-nineteenth century and recognized these numbers. They are important because they held information about the number of households, registered individuals and ages of individuals. We applied a red color filter to separate numerals from the document by taking advantage of the structure of the studied registers (numerals are written in red). We first used a CNN-based segmentation method for spotting these numerals. In the second part, we annotated a local Arabic handwritten digit dataset from the spotted numerals by selecting uni-digit ones and tested the Deep Transfer Learning method from large open Arabic handwritten digit datasets for digit recognition. We achieved promising results for recognizing digits in these historical documents. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

17 pages, 4813 KiB

Open AccessArticle

Leaf Image Recognition Based on Bag of Features

by Yaonan Zhang, Jing Cui, Zhaobin Wang, Jianfang Kang and Yufang Min

Appl. Sci. 2020, 10(15), 5177; https://doi.org/10.3390/app10155177 - 28 Jul 2020

Cited by 22 | Viewed by 4380

Abstract

Plants are ubiquitous in human life. Recognizing an unknown plant by its leaf image quickly is a very interesting and challenging research. With the development of image processing and pattern recognition, plant recognition based on image processing has become possible. Bag of features [...] Read more.

Plants are ubiquitous in human life. Recognizing an unknown plant by its leaf image quickly is a very interesting and challenging research. With the development of image processing and pattern recognition, plant recognition based on image processing has become possible. Bag of features (BOF) is one of the most powerful models for classification, which has been used for many projects and studies. Dual-output pulse-coupled neural network (DPCNN) has shown a good ability for texture features in image processing such as image segmentation. In this paper, a method based on BOF and DPCNN (BOF_DP) is proposed for leaf classification. BOF_DP achieved satisfactory results in many leaf image datasets. As it is hard to get a satisfactory effect on the large dataset by a single feature, a method (BOF_SC) improved from bag of contour fragments is used for shape feature extraction. BOF_DP and LDA (linear discriminant analysis) algorithms are, respectively, employed for textual feature extraction and reducing the feature dimensionality. Finally, both features are used for classification by a linear support vector machine (SVM), and the proposed method obtained higher accuracy on several typical leaf datasets than existing methods. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

16 pages, 5264 KiB

Open AccessArticle

A Smartphone-Based Cell Segmentation to Support Nasal Cytology

by Giovanni Dimauro, Davide Di Pierro, Francesca Deperte, Lorenzo Simone and Pio Raffaele Fina

Appl. Sci. 2020, 10(13), 4567; https://doi.org/10.3390/app10134567 - 30 Jun 2020

Cited by 4 | Viewed by 3093

Abstract

Rhinology studies the anatomy, physiology, and diseases affecting the nasal region—one of the most modern techniques to diagnose these diseases is nasal cytology, which involves microscopic analysis of the cells contained in the nasal mucosa. The standard clinical protocol regulates the compilation of [...] Read more.

Rhinology studies the anatomy, physiology, and diseases affecting the nasal region—one of the most modern techniques to diagnose these diseases is nasal cytology, which involves microscopic analysis of the cells contained in the nasal mucosa. The standard clinical protocol regulates the compilation of the rhino-cytogram by observing, for each slide, at least 50 fields under an optical microscope to evaluate the cell population and search for cells important for diagnosis. The time and effort required for the specialist to analyze a slide are significant. In this paper, we present a smartphones-based system to support cell segmentation on images acquired directly from the microscope. Then, the specialist can analyze the cells and the other elements extracted directly or, alternatively, he can send them to Rhino-cyt, a server system recently presented in the literature, that also performs the automatic cell classification, giving back the final rhinocytogram. This way he significantly reduces the time for diagnosing. The system crops cells with sensitivity = 0.96, which is satisfactory because it shows that cells are not overlooked as false negatives are few, and therefore largely sufficient to support the specialist effectively. The use of traditional image processing techniques to preprocess the images also makes the process sustainable from the computational point of view for medium–low end architectures and is battery-efficient on a mobile phone. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

14 pages, 1388 KiB

Open AccessArticle

Unconstrained Bilingual Scene Text Reading Using Octave as a Feature Extractor

by Direselign Addis Tadesse, Chuan-Ming Liu and Van-Dai Ta

Appl. Sci. 2020, 10(13), 4474; https://doi.org/10.3390/app10134474 - 28 Jun 2020

Cited by 2 | Viewed by 2012

Abstract

Reading text and unified text detection and recognition from natural images are the most challenging applications in computer vision and document analysis. Previously proposed end-to-end scene text reading methods do not consider the frequency of input images at feature extraction, which slows down [...] Read more.

Reading text and unified text detection and recognition from natural images are the most challenging applications in computer vision and document analysis. Previously proposed end-to-end scene text reading methods do not consider the frequency of input images at feature extraction, which slows down the system, requires more memory, and recognizes text inaccurately. In this paper, we proposed an octave convolution (OctConv) feature extractor and a time-restricted attention encoder-decoder module for end-to-end scene text reading. The OctConv can extract features by factorizing the input image based on their frequency. It is a direct replacement of convolutions, orthogonal and complementary, for reducing redundancies and helps to boost the reading text through low memory requirements at a faster speed. In the text reading process, features are first extracted from the input image using Feature Pyramid Network (FPN) with OctConv Residual Network with depth 50 (ResNet50). Then, a Region Proposal Network (RPN) is applied to predict the location of the text area by using extracted features. Finally, a time-restricted attention encoder-decoder module is applied after the Region of Interest (RoI) pooling is performed. A bilingual real and synthetic scene text dataset is prepared for training and testing the proposed model. Additionally, well-known datasets including ICDAR2013, ICDAR2015, and Total Text are used for fine-tuning and evaluating its performance with previously proposed state-of-the-art methods. The proposed model shows promising results on both regular and irregular or curved text detection and reading tasks. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

17 pages, 4377 KiB

Open AccessArticle

Data-Driven Redundant Transform Based on Parseval Frames

by Min Zhang, Yunhui Shi, Na Qi and Baocai Yin

Appl. Sci. 2020, 10(8), 2891; https://doi.org/10.3390/app10082891 - 22 Apr 2020

Cited by 4 | Viewed by 1769

Abstract

The sparsity of images in a certain transform domain or dictionary has been exploited in many image processing applications. Both classic transforms and sparsifying transforms reconstruct images by a linear combination of a small basis of the transform. Both kinds of transform are [...] Read more.

The sparsity of images in a certain transform domain or dictionary has been exploited in many image processing applications. Both classic transforms and sparsifying transforms reconstruct images by a linear combination of a small basis of the transform. Both kinds of transform are non-redundant. However, natural images admit complicated textures and structures, which can hardly be sparsely represented by square transforms. To solve this issue, we propose a data-driven redundant transform based on Parseval frames (DRTPF) by applying the frame and its dual frame as the backward and forward transform operators, respectively. Benefitting from this pairwise use of frames, the proposed model combines a synthesis sparse system and an analysis sparse system. By enforcing the frame pair to be Parseval frames, the singular values and condition number of the learnt redundant frames, which are efficient values for measuring the quality of the learnt sparsifying transforms, are forced to achieve an optimal state. We formulate a transform pair (i.e., frame pair) learning model and a two-phase iterative algorithm, analyze the robustness of the proposed DRTPF and the convergence of the corresponding algorithm, and demonstrate the effectiveness of our proposed DRTPF by analyzing its robustness against noise and sparsification errors. Extensive experimental results on image denoising show that our proposed model achieves superior denoising performance, in terms of subjective and objective quality, compared to traditional sparse models. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

13 pages, 243 KiB

Open AccessArticle

Comparison of Image Fusion Techniques Using Satellite Pour l’Observation de la Terre (SPOT) 6 Satellite Imagery

by Paidamwoyo Mhangara, Willard Mapurisa and Naledzani Mudau

Appl. Sci. 2020, 10(5), 1881; https://doi.org/10.3390/app10051881 - 10 Mar 2020

Cited by 39 | Viewed by 4938

Abstract

Preservation of spectral and spatial information is an important requirement for most quantitative remote sensing applications. In this study, we use image quality metrics to evaluate the performance of several image fusion techniques to assess the spectral and spatial quality of pansharpened images. [...] Read more.

Preservation of spectral and spatial information is an important requirement for most quantitative remote sensing applications. In this study, we use image quality metrics to evaluate the performance of several image fusion techniques to assess the spectral and spatial quality of pansharpened images. We evaluated twelve pansharpening algorithms in this study; the Local Mean and Variance Matching (IMVM) algorithm was the best in terms of spectral consistency and synthesis followed by the ratio component substitution (RCS) algorithm. Whereas the IMVM and RCS image fusion techniques showed better results compared to other pansharpening methods, it is pertinent to highlight that our study also showed the credibility of other pansharpening algorithms in terms of spatial and spectral consistency as shown by the high correlation coefficients achieved in all methods. We noted that the algorithms that ranked higher in terms of spectral consistency and synthesis were outperformed by other competing algorithms in terms of spatial consistency. The study, therefore, concludes that the selection of image fusion techniques is driven by the requirements of remote sensing application and a careful trade-off is necessary to account for the impact of scene radiometry, image sharpness, spatial and spectral consistency, and computational overhead. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

16 pages, 38070 KiB

Open AccessArticle

A Stronger Aadaptive Local Dimming Method with Details Preservation

by Tao Zhang, Wenli Du, Hao Wang, Qin Zeng and Long Fan

Appl. Sci. 2020, 10(5), 1820; https://doi.org/10.3390/app10051820 - 6 Mar 2020

Cited by 5 | Viewed by 3783

Abstract

Local dimming technology focuses on improving the contrast ratio of the displayed images for a great visual perception. It consists of backlight extraction and pixel compensation. Considering a single existing backlight extraction algorithm can hardly adapt to images with diverse characteristics and rich [...] Read more.

Local dimming technology focuses on improving the contrast ratio of the displayed images for a great visual perception. It consists of backlight extraction and pixel compensation. Considering a single existing backlight extraction algorithm can hardly adapt to images with diverse characteristics and rich details, we propose a stronger adaptive local dimming method with details preservation in this paper. This method, combining the advantages of some existing methods and introducing the combination of the subjective evaluation and the objective evaluation, obtains a stronger adaptation compared with others. Besides, to offset the luminance reduction caused in the backlight extraction process, we improve the bi-histogram equalization algorithm and propose a new pixel compensation method. To preserve image details, the Retinex theory is adopted to separate details. Experimental results demonstrate the effect of the proposed method on contrast ratio improvement and details preservation. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

21 pages, 8292 KiB

Open AccessArticle

Stable Sparse Model with Non-Tight Frame

by Min Zhang, Yunhui Shi, Na Qi and Baocai Yin

Appl. Sci. 2020, 10(5), 1771; https://doi.org/10.3390/app10051771 - 4 Mar 2020

Cited by 1 | Viewed by 2499

Abstract

Overcomplete representation is attracting interest in image restoration due to its potential to generate sparse representations of signals. However, the problem of seeking sparse representation must be unstable in the presence of noise. Restricted Isometry Property (RIP), playing a crucial role in providing [...] Read more.

Overcomplete representation is attracting interest in image restoration due to its potential to generate sparse representations of signals. However, the problem of seeking sparse representation must be unstable in the presence of noise. Restricted Isometry Property (RIP), playing a crucial role in providing stable sparse representation, has been ignored in the existing sparse models as it is hard to integrate into the conventional sparse models as a regularizer. In this paper, we propose a stable sparse model with non-tight frame (SSM-NTF) via applying the corresponding frame condition to approximate RIP. Our SSM-NTF model takes into account the advantage of the traditional sparse model, and meanwhile contains RIP and closed-form expression of sparse coefficients which ensure stable recovery. Moreover, benefitting from the pair-wise of the non-tight frame (the original frame and its dual frame), our SSM-NTF model combines a synthesis sparse system and an analysis sparse system. By enforcing the frame bounds and applying a second-order truncated series to approximate the inverse frame operator, we formulate a dictionary pair (frame pair) learning model along with a two-phase iterative algorithm. Extensive experimental results on image restoration tasks such as denoising, super resolution and inpainting show that our proposed SSM-NTF achieves superior recovery performance in terms of both subjective and objective quality. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

13 pages, 32899 KiB

Open AccessArticle

Real-Time Haze Removal Using Normalised Pixel-Wise Dark-Channel Prior and Robust Atmospheric-Light Estimation

by Yutaro Iwamoto, Naoaki Hashimoto and Yen-Wei Chen

Appl. Sci. 2020, 10(3), 1165; https://doi.org/10.3390/app10031165 - 9 Feb 2020

Cited by 12 | Viewed by 3546

Abstract

This study proposes real-time haze removal from a single image using normalised pixel-wise dark-channel prior (DCP). DCP assumes that at least one RGB colour channel within most local patches in a haze-free image has a low-intensity value. Since the spatial resolution of the [...] Read more.

This study proposes real-time haze removal from a single image using normalised pixel-wise dark-channel prior (DCP). DCP assumes that at least one RGB colour channel within most local patches in a haze-free image has a low-intensity value. Since the spatial resolution of the transmission map depends on the patch size and it loses the detailed structure with large patch sizes, original work refines the transmission map using an image-matting technique. However, it requires high computational cost and is not adequate for real-time application. To solve these problems, we use normalised pixel-wise haze estimation without losing the detailed structure of the transmission map. This study also proposes robust atmospheric-light estimation using a coarse-to-fine search strategy and down-sampled haze estimation for acceleration. Experiments with actual and simulated haze images showed that the proposed method achieves real-time results of visually and quantitatively acceptable quality compared with other conventional methods of haze removal. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

18 pages, 5524 KiB

Open AccessArticle

Temporal Saliency-Based Suspicious Behavior Pattern Detection

by Kyung Joo Cheoi

Appl. Sci. 2020, 10(3), 1020; https://doi.org/10.3390/app10031020 - 4 Feb 2020

Cited by 8 | Viewed by 3198

Abstract

The topic of suspicious behavior detection has been one of the most emergent research themes in computer vision, video analysis, and monitoring. Due to the huge number of CCTV (closed-circuit television) systems, it is not easy for people to manually identify CCTV for [...] Read more.

The topic of suspicious behavior detection has been one of the most emergent research themes in computer vision, video analysis, and monitoring. Due to the huge number of CCTV (closed-circuit television) systems, it is not easy for people to manually identify CCTV for suspicious motion monitoring. This paper is concerned with an automatic suspicious behavior detection method using a CCTV video stream. Observers generally focus their attention on behaviors that vary in terms of magnitude or gradient of motion and behave differently in rules of motion with other objects. Based on these facts, the proposed method detected suspicious behavior with a temporal saliency map by combining the moving reactivity features of motion magnitude and gradient extracted by optical flow. It has been tested on various video clips that contain suspicious behavior. The experimental results show that the performance of the proposed method is good at detecting the six designated types of suspicious behavior examined: sudden running, colliding, falling, jumping, fighting, and slipping. The proposed method achieved an average accuracy of 93.89%, a precision of 96.21% and a recall of 94.90%. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

14 pages, 4067 KiB

Open AccessArticle

Image Super-Resolution Based on CNN Using Multilabel Gene Expression Programming

by Jiali Tang, Chenrong Huang, Jian Liu and Hongjin Zhu

Appl. Sci. 2020, 10(3), 854; https://doi.org/10.3390/app10030854 - 25 Jan 2020

Cited by 5 | Viewed by 2822

Abstract

Current mainstream super-resolution algorithms based on deep learning use a deep convolution neural network (CNN) framework to realize end-to-end learning from low-resolution (LR) image to high-resolution (HR) images, and have achieved good image restoration effects. However, as the number of layers in the [...] Read more.

Current mainstream super-resolution algorithms based on deep learning use a deep convolution neural network (CNN) framework to realize end-to-end learning from low-resolution (LR) image to high-resolution (HR) images, and have achieved good image restoration effects. However, as the number of layers in the network is increased, better results are not necessarily obtained, and there will be problems such as slow training convergence, mismatched sample blocks, and unstable image restoration results. We propose a preclassified deep-learning algorithm (MGEP-SRCNN) using Multilabel Gene Expression Programming (MGEP), which screens out a sample sub-bank with high relevance to the target image before image block extraction, preclassifies samples in a multilabel framework, and then performs nonlinear mapping and image reconstruction. The algorithm is verified through standard images, and better objective image quality is obtained. The restoration effect under different magnification conditions is also better. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

16 pages, 2496 KiB

Open AccessArticle

Image Registration Algorithm Based on Convolutional Neural Network and Local Homography Transformation

by Yuanwei Wang, Mei Yu, Gangyi Jiang, Zhiyong Pan and Jiqiang Lin

Appl. Sci. 2020, 10(3), 732; https://doi.org/10.3390/app10030732 - 21 Jan 2020

Cited by 10 | Viewed by 3814

Abstract

In order to overcome the poor robustness of traditional image registration algorithms in illuminating and solving the problem of low accuracy of a learning-based image homography matrix estimation algorithm, an image registration algorithm based on convolutional neural network (CNN) and local homography transformation [...] Read more.

In order to overcome the poor robustness of traditional image registration algorithms in illuminating and solving the problem of low accuracy of a learning-based image homography matrix estimation algorithm, an image registration algorithm based on convolutional neural network (CNN) and local homography transformation is proposed. Firstly, to ensure the diversity of samples, a sample and label generation method based on moving direct linear transformation (MDLT) is designed. The generated samples and labels can effectively reflect the local characteristics of images and are suitable for training the CNN model with which multiple pairs of local matching points between two images to be registered can be calculated. Then, the local homography matrices between the two images are estimated by using the MDLT and finally the image registration can be realized. The experimental results show that the proposed image registration algorithm achieves higher accuracy than other commonly used algorithms such as the SIFT, ORB, ECC, and APAP algorithms, as well as another two learning-based algorithms, and it has good robustness for different types of illumination imaging. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

15 pages, 2146 KiB

Open AccessArticle

Optical Flow-Based Fast Motion Parameters Estimation for Affine Motion Compensation

by Antoine Chauvet, Yoshihiro Sugaya, Tomo Miyazaki and Shinichiro Omachi

Appl. Sci. 2020, 10(2), 729; https://doi.org/10.3390/app10020729 - 20 Jan 2020

Cited by 3 | Viewed by 3698

Abstract

This study proposes a lightweight solution to estimate affine parameters in affine motion compensation. Most of the current approaches start with an initial approximation based on the standard motion estimation, which only estimates the translation parameters. From there, iterative methods are used to [...] Read more.

This study proposes a lightweight solution to estimate affine parameters in affine motion compensation. Most of the current approaches start with an initial approximation based on the standard motion estimation, which only estimates the translation parameters. From there, iterative methods are used to find the best parameters, but they require a significant amount of time. The proposed method aims to speed up the process in two ways, first, skip evaluating affine prediction when it is likely to bring no encoding efficiency benefit, and second, by estimating better initial values for the iteration process. We use the optical flow between the reference picture and the current picture to estimate quickly the best encoding mode and get a better initial estimation. We achieve a reduction in encoding time over the reference of half when compared to the state of the art, with a loss in efficiency below 1%. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Graphical abstract

16 pages, 1506 KiB

Open AccessArticle

The Classification of Inertinite Macerals in Coal Based on the Multifractal Spectrum Method

by Man Liu, Peizhen Wang, Simin Chen and Dailin Zhang

Appl. Sci. 2019, 9(24), 5509; https://doi.org/10.3390/app9245509 - 14 Dec 2019

Cited by 9 | Viewed by 3144

Abstract

Considering the heterogeneous nature and non-stationary property of inertinite components, we propose a texture description method with a set of multifractal descriptors to identify different macerals with few but effective features. This method is based on the multifractal spectrum calculated from the method [...] Read more.

Considering the heterogeneous nature and non-stationary property of inertinite components, we propose a texture description method with a set of multifractal descriptors to identify different macerals with few but effective features. This method is based on the multifractal spectrum calculated from the method of multifractal detrended fluctuation analysis (MF-DFA). Additionally, microscopic images of inertinite macerals were analyzed, which were verified to possess the property of multifractal. Simultaneously, we made an attempt to assess the influences of noise and blur on multifractal descriptors; the multifractal analysis was proven to be robust and immune to image quality. Finally, a classification model with a support vector machine (SVM) was built to distinguish different inertinite macerals from microscopic images of coal. The performance evaluation proves that the proposed descriptors based on multifractal spectrum can be successfully applied in the classification of inertinite macerals. The average classification precision can reach 95.33%, higher than that of description method with gray level co-occurrence matrix (GLCM; about 7.99%). Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

30 pages, 6418 KiB

Open AccessArticle

An Approach for the Pan Sharpening of Very High Resolution Satellite Images Using a CIELab Color Based Component Substitution Algorithm

by Alireza Rahimzadeganasl, Ugur Alganci and Cigdem Goksel

Appl. Sci. 2019, 9(23), 5234; https://doi.org/10.3390/app9235234 - 1 Dec 2019

Cited by 9 | Viewed by 3949

Abstract

Recent very high spatial resolution (VHR) remote sensing satellites provide high spatial resolution panchromatic (Pan) images in addition to multispectral (MS) images. The pan sharpening process has a critical role in image processing tasks and geospatial information extraction from satellite images. In this [...] Read more.

Recent very high spatial resolution (VHR) remote sensing satellites provide high spatial resolution panchromatic (Pan) images in addition to multispectral (MS) images. The pan sharpening process has a critical role in image processing tasks and geospatial information extraction from satellite images. In this research, CIELab color based component substitution Pan sharpening algorithm was proposed for Pan sharpening of the Pleiades VHR images. The proposed method was compared with the state-of-the-art Pan sharpening methods, such as IHS, EHLERS, NNDiffuse and GIHS. The selected study region included ten test sites, each of them representing complex landscapes with various land categories, to evaluate the performance of Pan sharpening methods in varying land surface characteristics. The spatial and spectral performance of the Pan sharpening methods were evaluated by eleven accuracy metrics and visual interpretation. The results of the evaluation indicated that proposed CIELab color-based method reached promising results and improved the spectral and spatial information preservation. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

Review

Jump to: Editorial, Research

12 pages, 788 KiB

Open AccessReview

Dental Images Recognition Technology and Applications: A Literature Review

by María Prados-Privado, Javier García Villalón, Carlos Hugo Martínez-Martínez and Carlos Ivorra

Appl. Sci. 2020, 10(8), 2856; https://doi.org/10.3390/app10082856 - 20 Apr 2020

Cited by 33 | Viewed by 4970

Abstract

Neural networks are increasingly being used in the field of dentistry. The aim of this literature review was to visualize the state of the art of artificial intelligence in dental applications, such as the detection of teeth, caries, filled teeth, crown, prosthesis, dental [...] Read more.

Neural networks are increasingly being used in the field of dentistry. The aim of this literature review was to visualize the state of the art of artificial intelligence in dental applications, such as the detection of teeth, caries, filled teeth, crown, prosthesis, dental implants and endodontic treatment. A search was conducted in PubMed, the Institute of Electrical and Electronics Engineers (IEEE) Xplore and arXiv.org. Data extraction was performed independently by two reviewers. Eighteen studies were included. The variable teeth was the most analyzed (n = 9), followed by caries (n = 7). No studies detecting dental implants and filled teeth were found. Only two studies investigated endodontic applications. Panoramic radiographies were the most common image employed (n = 5), followed by periapical images (n = 3). Near-infrared light transillumination images were employed in two studies and bitewing and computed tomography (CT) were employed in one study. The included articles used a wide variety of neuronal networks to detect the described variables. In addition, the database used also had a great heterogeneity in the number of images. A standardized methodology should be used in order to increase the compatibility and robustness between studies because of the heterogeneity in the image database, type, neural architecture and results. Full article

(This article belongs to the Special Issue Advances in Image Processing, Analysis and Recognition Technology)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Advances in Image Processing, Analysis and Recognition Technology

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (23 papers)

Editorial

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI