Pub Date : 2012-10-01DOI: 10.1109/IPTA.2012.6469526
E. Pastor, E. Planas
Wildfire infrared monitoring is nowadays applied to different problems related to fire prevention, fire suppression and fire behaviour analysis. In terms of research, infrared thermography offers unique capabilities although it is constantly challenging the scientific community to develop sound process imagery methodologies in order to obtain valuable and reliable information about fire phenomena. In this paper we show some infrared thermography applications that we have recently developed to provide solutions on fuel mapping, fire behaviour analysis, fire suppression and fire effects assessment. We highlight the advantages and drawbacks of all of them and present future problems that can be tackled with this type of fire monitoring techniques.
{"title":"Infrared imagery on wildfire research. Some examples of sound capabilities and applications","authors":"E. Pastor, E. Planas","doi":"10.1109/IPTA.2012.6469526","DOIUrl":"https://doi.org/10.1109/IPTA.2012.6469526","url":null,"abstract":"Wildfire infrared monitoring is nowadays applied to different problems related to fire prevention, fire suppression and fire behaviour analysis. In terms of research, infrared thermography offers unique capabilities although it is constantly challenging the scientific community to develop sound process imagery methodologies in order to obtain valuable and reliable information about fire phenomena. In this paper we show some infrared thermography applications that we have recently developed to provide solutions on fuel mapping, fire behaviour analysis, fire suppression and fire effects assessment. We highlight the advantages and drawbacks of all of them and present future problems that can be tackled with this type of fire monitoring techniques.","PeriodicalId":267290,"journal":{"name":"2012 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126632846","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-10-01DOI: 10.1109/IPTA.2012.6469502
J. Kamarainen
In applications of computer vision and image analysis, Gabor filters have maintained their popularity in feature extraction for almost three decades. The original reason that draw attention was the similarity between Gabor filters and the receptive field of simple cells in the visual cortex. A more practical reason is their success in many applications, e.g., face detection and recognition, iris recognition and fingerprint matching, where Gabor feature based methods are among the top performers. The derivation of Gabor features is elegant through the fundamental domains of signal processing: space (time) and frequency. Topped with many practical and computational advantages we will see their use also in future applications.
{"title":"Gabor features in image analysis","authors":"J. Kamarainen","doi":"10.1109/IPTA.2012.6469502","DOIUrl":"https://doi.org/10.1109/IPTA.2012.6469502","url":null,"abstract":"In applications of computer vision and image analysis, Gabor filters have maintained their popularity in feature extraction for almost three decades. The original reason that draw attention was the similarity between Gabor filters and the receptive field of simple cells in the visual cortex. A more practical reason is their success in many applications, e.g., face detection and recognition, iris recognition and fingerprint matching, where Gabor feature based methods are among the top performers. The derivation of Gabor features is elegant through the fundamental domains of signal processing: space (time) and frequency. Topped with many practical and computational advantages we will see their use also in future applications.","PeriodicalId":267290,"journal":{"name":"2012 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123463413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-10-01DOI: 10.1109/IPTA.2012.6469550
Amel Ksibi, Mouna Dammak, A. Ammar, M. Mejdoub, C. Amar
Automatic photo annotation task aims to describe the semantic content by detecting high level concepts in order to further facilitate concept based video retrieval. Most of existing approaches are based on independent semantic concept detectors without considering the contextual correlation between concepts. This drawback has its impact over the efficiency of such systems. Recently, harnessing contextual information to improve the effectiveness of concepts detection becomes a promising direction in such field. In this paper, we propose a new contextbased annotation refinement process. For this purpose, we define a new semantic measure called “Second Order Co-occurence Flickr context similarity” (SOCFCS) which aims to extract the semantic context correlation between two concepts by exploring Flickr resources (Flickr related-tags). Our measure is an extension of FCS measure by taking into consideration the FCS values of common Flickr related-tags of the two target concepts. Our proposed measure is applied to build a concept network which models the semantic context inter-relationships among concepts. A Random Walk with Restart process is performed over this network to refine the annotation results by exploring the contextual correlation among concepts. Experimental studies are conducted on ImageCLEF 2011 Collection containing 10000 images and 99 concepts. The results demonstrate the effectiveness of our proposed approach.
照片自动标注任务旨在通过检测高级概念来描述语义内容，从而进一步促进基于概念的视频检索。现有的方法大多是基于独立的语义概念检测器，没有考虑概念之间的上下文相关性。这一缺点影响了这类系统的效率。近年来，利用上下文信息来提高概念检测的有效性成为该领域一个很有前途的方向。在本文中，我们提出了一种新的基于上下文的标注改进过程。为此，我们定义了一个新的语义度量，称为“二阶共现Flickr上下文相似度”(SOCFCS)，旨在通过探索Flickr资源(Flickr相关标签)来提取两个概念之间的语义上下文相关性。我们的度量是FCS度量的扩展，考虑了两个目标概念的常见Flickr相关标签的FCS值。我们提出的方法被用于建立一个概念网络，该网络对概念之间的语义上下文相互关系进行建模。在该网络上执行随机行走(Random Walk with Restart)过程，通过探索概念之间的上下文相关性来改进注释结果。在包含10000张图片和99个概念的ImageCLEF 2011 Collection上进行实验研究。结果证明了我们所提出的方法的有效性。
{"title":"Flickr-based semantic context to refine automatic photo annotation","authors":"Amel Ksibi, Mouna Dammak, A. Ammar, M. Mejdoub, C. Amar","doi":"10.1109/IPTA.2012.6469550","DOIUrl":"https://doi.org/10.1109/IPTA.2012.6469550","url":null,"abstract":"Automatic photo annotation task aims to describe the semantic content by detecting high level concepts in order to further facilitate concept based video retrieval. Most of existing approaches are based on independent semantic concept detectors without considering the contextual correlation between concepts. This drawback has its impact over the efficiency of such systems. Recently, harnessing contextual information to improve the effectiveness of concepts detection becomes a promising direction in such field. In this paper, we propose a new contextbased annotation refinement process. For this purpose, we define a new semantic measure called “Second Order Co-occurence Flickr context similarity” (SOCFCS) which aims to extract the semantic context correlation between two concepts by exploring Flickr resources (Flickr related-tags). Our measure is an extension of FCS measure by taking into consideration the FCS values of common Flickr related-tags of the two target concepts. Our proposed measure is applied to build a concept network which models the semantic context inter-relationships among concepts. A Random Walk with Restart process is performed over this network to refine the annotation results by exploring the contextual correlation among concepts. Experimental studies are conducted on ImageCLEF 2011 Collection containing 10000 images and 99 concepts. The results demonstrate the effectiveness of our proposed approach.","PeriodicalId":267290,"journal":{"name":"2012 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114637278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-10-01DOI: 10.1109/IPTA.2012.6469560
Yanal Wazaefi, Sébastien Paris, B. Fertil
In this paper, we investigated to what extent the melanoma diagnosis can be impacted by an automatic system using dermoscopic images of pigmented skin lesions. Nine dermatologists were asked to give their diagnosis about 1097 dermoscopic images of skin lesions, including 88 histopathologically confirmed melanomas. The automatic diagnosis of black tumors was based on Local Binary Patterns (LBP) without segmentation of the dermoscopic images. The classification was performed using a simple linear support vector machines (SVM). The classifier showed a comparable performance with respect to dermatologists (AUC: 0.85). It appeared that a fusion of dermatologist's diagnosis with the automatic diagnosis improves the overall performances. We proposed a simple fusion strategy (highest-risk approach) with the automatic diagnosis, which improves the dermatologists' daily practice performance.
{"title":"Contribution of a classifier of skin lesions to the dermatologist's decision","authors":"Yanal Wazaefi, Sébastien Paris, B. Fertil","doi":"10.1109/IPTA.2012.6469560","DOIUrl":"https://doi.org/10.1109/IPTA.2012.6469560","url":null,"abstract":"In this paper, we investigated to what extent the melanoma diagnosis can be impacted by an automatic system using dermoscopic images of pigmented skin lesions. Nine dermatologists were asked to give their diagnosis about 1097 dermoscopic images of skin lesions, including 88 histopathologically confirmed melanomas. The automatic diagnosis of black tumors was based on Local Binary Patterns (LBP) without segmentation of the dermoscopic images. The classification was performed using a simple linear support vector machines (SVM). The classifier showed a comparable performance with respect to dermatologists (AUC: 0.85). It appeared that a fusion of dermatologist's diagnosis with the automatic diagnosis improves the overall performances. We proposed a simple fusion strategy (highest-risk approach) with the automatic diagnosis, which improves the dermatologists' daily practice performance.","PeriodicalId":267290,"journal":{"name":"2012 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131089827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-10-01DOI: 10.1109/IPTA.2012.6469564
S. Banerji, A. Sinha, Chengjun Liu
Several new image descriptors are presented in this paper that combine color, texture and shape information to create feature vectors for scene and object image classification. In particular, first, a new three dimensional Local Binary Patterns (3D-LBP) descriptor is proposed for color image local feature extraction. Second, three novel color HWML (HOG of Wavelet of Multiplanar LBP) descriptors are derived by computing the histogram of the orientation gradients of the Haar wavelet transformation of the original image and the 3D-LBP images. Third, the Enhanced Fisher Model (EFM) is applied for discriminatory feature extraction and the nearest neighbor classification rule is used for image classification. Finally, the Caltech 256 object categories database and the MIT scene dataset are used to show the feasibility of the proposed new methods.
本文提出了几种新的图像描述符，将颜色、纹理和形状信息结合起来，生成用于场景和目标图像分类的特征向量。首先，提出了一种用于彩色图像局部特征提取的三维局部二值模式描述符(3D-LBP)。其次，通过计算原始图像和3D-LBP图像的Haar小波变换方向梯度直方图，推导出3种新的彩色HWML (HOG of Wavelet of Multiplanar LBP)描述子;第三，采用增强Fisher模型(Enhanced Fisher Model, EFM)进行区别特征提取，并采用最近邻分类规则进行图像分类。最后，利用Caltech 256对象分类数据库和MIT场景数据集验证了所提方法的可行性。
{"title":"Novel color HWML descriptors for scene and object image classification","authors":"S. Banerji, A. Sinha, Chengjun Liu","doi":"10.1109/IPTA.2012.6469564","DOIUrl":"https://doi.org/10.1109/IPTA.2012.6469564","url":null,"abstract":"Several new image descriptors are presented in this paper that combine color, texture and shape information to create feature vectors for scene and object image classification. In particular, first, a new three dimensional Local Binary Patterns (3D-LBP) descriptor is proposed for color image local feature extraction. Second, three novel color HWML (HOG of Wavelet of Multiplanar LBP) descriptors are derived by computing the histogram of the orientation gradients of the Haar wavelet transformation of the original image and the 3D-LBP images. Third, the Enhanced Fisher Model (EFM) is applied for discriminatory feature extraction and the nearest neighbor classification rule is used for image classification. Finally, the Caltech 256 object categories database and the MIT scene dataset are used to show the feasibility of the proposed new methods.","PeriodicalId":267290,"journal":{"name":"2012 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"220 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131902823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-10-01DOI: 10.1109/IPTA.2012.6469482
Dimitrios Alexios Karras
Summary form only given. Magnetic resonance spectroscopic imaging (MRSI) combines quantitation of MRS signals and imaging algorithms in order to obtain spatially localized MRS spectra corresponding to a unique clinical subject. MRSI is a relatively new imaging modality for clinical applications compared to MRS spectroscopy quantitation methodologies. Both are related to NMR scanners and spectroscopy. The goal of this plenary talk will be to present a computational intelligent framework for processing such complex spectra modalities towards designing an efficient CBIR system for NMR potential clinical applications. These methodologies will be based on Nonlinear Signal Processing techniques including Dynamical Systems Analysis, Global Optimization methods including Genetic Algorithms as well as on Fuzzy Systems Theory involving development and evaluation of suitable complex Fuzzy Descriptors. A series of experiments illustrate the feasibility and potential of the proposed approaches using synthetic images and model MRS signals derived from benchmark MRS spectra, towards successful NMR spectra retrieval in clinical applications.
{"title":"A computional intelligence framework for NMR spectroscopy imaging and retrieval","authors":"Dimitrios Alexios Karras","doi":"10.1109/IPTA.2012.6469482","DOIUrl":"https://doi.org/10.1109/IPTA.2012.6469482","url":null,"abstract":"Summary form only given. Magnetic resonance spectroscopic imaging (MRSI) combines quantitation of MRS signals and imaging algorithms in order to obtain spatially localized MRS spectra corresponding to a unique clinical subject. MRSI is a relatively new imaging modality for clinical applications compared to MRS spectroscopy quantitation methodologies. Both are related to NMR scanners and spectroscopy. The goal of this plenary talk will be to present a computational intelligent framework for processing such complex spectra modalities towards designing an efficient CBIR system for NMR potential clinical applications. These methodologies will be based on Nonlinear Signal Processing techniques including Dynamical Systems Analysis, Global Optimization methods including Genetic Algorithms as well as on Fuzzy Systems Theory involving development and evaluation of suitable complex Fuzzy Descriptors. A series of experiments illustrate the feasibility and potential of the proposed approaches using synthetic images and model MRS signals derived from benchmark MRS spectra, towards successful NMR spectra retrieval in clinical applications.","PeriodicalId":267290,"journal":{"name":"2012 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"208 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133829320","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-10-01DOI: 10.1109/IPTA.2012.6469537
M. R. Boussema, M. Naceur, H. Elmannai
In this paper, we aim to classify remotely sensed images for land characterisation. The major goal is approaching the natural nonlinear mixture for band observation and then dimension reduction by supervised classification. After that, an unsupervised method combining feature extraction and SVM in investigating to discriminate the land cover for SPOT 4 satellite image. In this technique, training data base are wavelet features that are extracted from a subset of sources.
{"title":"Perceptron nonlinear blind source separation for feature extraction and image classification","authors":"M. R. Boussema, M. Naceur, H. Elmannai","doi":"10.1109/IPTA.2012.6469537","DOIUrl":"https://doi.org/10.1109/IPTA.2012.6469537","url":null,"abstract":"In this paper, we aim to classify remotely sensed images for land characterisation. The major goal is approaching the natural nonlinear mixture for band observation and then dimension reduction by supervised classification. After that, an unsupervised method combining feature extraction and SVM in investigating to discriminate the land cover for SPOT 4 satellite image. In this technique, training data base are wavelet features that are extracted from a subset of sources.","PeriodicalId":267290,"journal":{"name":"2012 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115913941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-10-01DOI: 10.1109/IPTA.2012.6469563
F. Derraz, L. Peyrodie, J. Thiran, A. Taleb-Ahmed, G. Forzy
In this paper, we propose a new framework for Binary Active Contours (AC) that incorporates a new texture descriptor. The texture descriptor is split into inside/ outside region descriptors. Both the inside and outside texture descriptors discriminate the texture using Kullback-Leibler distance. Using these two descriptors, the AC incorporates both learned textures. This formulation has two main advantages. Firstly, by discriminating independently the foreground/background textures. Secondly, by incorporating both the learned inside/outside texture. Our segmentation model based AC model is formulated in Total variation framework using characteristic function framework. We propose a fast Bregman split implementation of our segmentation algorithm based on the primal-dual formulation. Finally, we show results on some challenging images to illustrate texture segmentations that are possible.
{"title":"Binary Active Contours using both inside and outside texture descriptors","authors":"F. Derraz, L. Peyrodie, J. Thiran, A. Taleb-Ahmed, G. Forzy","doi":"10.1109/IPTA.2012.6469563","DOIUrl":"https://doi.org/10.1109/IPTA.2012.6469563","url":null,"abstract":"In this paper, we propose a new framework for Binary Active Contours (AC) that incorporates a new texture descriptor. The texture descriptor is split into inside/ outside region descriptors. Both the inside and outside texture descriptors discriminate the texture using Kullback-Leibler distance. Using these two descriptors, the AC incorporates both learned textures. This formulation has two main advantages. Firstly, by discriminating independently the foreground/background textures. Secondly, by incorporating both the learned inside/outside texture. Our segmentation model based AC model is formulated in Total variation framework using characteristic function framework. We propose a fast Bregman split implementation of our segmentation algorithm based on the primal-dual formulation. Finally, we show results on some challenging images to illustrate texture segmentations that are possible.","PeriodicalId":267290,"journal":{"name":"2012 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"184 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116392670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-10-01DOI: 10.1109/IPTA.2012.6469503
H. K. Ekenel
Summary form only given. In the past several decades, facial image analysis has attracted continuous attention in computer vision, pattern recognition and machine learning areas, owing to its scientific challenges in both psychological interpretation and computational simulation, as well as its huge potential in real-world applications. Much progress has been achieved in the last two decades; however, researchers in the field also meet bafflement and challenges on the comprehensive and unbiased evaluation of the related technologies, which may prevent them from discovering the actual state of the art. BeFIT - Benchmarking Facial Image Analysis Technologies- is an international collaborative effort on standardizing the evaluation of facial image analysis technologies. The objective is to bring together different face analysis evaluations and provide a medium for researchers to discuss about different aspects of face analysis. This interaction would also lead to new datasets or combination of existing datasets. The BeFIT webpage (URL: http://face.cs.kit.edu/befit) is planned to serve as a repository of facial image analysis technologies benchmarks and the regular workshops are intended to serve as a medium where the researchers can discuss about different aspects of face analysis. In this talk, the Benchmarking Facial Image Analysis Technologies -BeFIT initiative will be introduced and an overview of the proposed challenges, benchmarks, and the provided data sets within the BeFIT framework will be presented.
{"title":"Benchmarking Facial Image Analysis Technologies (BeFIT)","authors":"H. K. Ekenel","doi":"10.1109/IPTA.2012.6469503","DOIUrl":"https://doi.org/10.1109/IPTA.2012.6469503","url":null,"abstract":"Summary form only given. In the past several decades, facial image analysis has attracted continuous attention in computer vision, pattern recognition and machine learning areas, owing to its scientific challenges in both psychological interpretation and computational simulation, as well as its huge potential in real-world applications. Much progress has been achieved in the last two decades; however, researchers in the field also meet bafflement and challenges on the comprehensive and unbiased evaluation of the related technologies, which may prevent them from discovering the actual state of the art. BeFIT - Benchmarking Facial Image Analysis Technologies- is an international collaborative effort on standardizing the evaluation of facial image analysis technologies. The objective is to bring together different face analysis evaluations and provide a medium for researchers to discuss about different aspects of face analysis. This interaction would also lead to new datasets or combination of existing datasets. The BeFIT webpage (URL: http://face.cs.kit.edu/befit) is planned to serve as a repository of facial image analysis technologies benchmarks and the regular workshops are intended to serve as a medium where the researchers can discuss about different aspects of face analysis. In this talk, the Benchmarking Facial Image Analysis Technologies -BeFIT initiative will be introduced and an overview of the proposed challenges, benchmarks, and the provided data sets within the BeFIT framework will be presented.","PeriodicalId":267290,"journal":{"name":"2012 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125603275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-10-01DOI: 10.1109/IPTA.2012.6469534
A. Chetouani, Azeddine Beghdadi, A. Bouzerdoum, Mohamed Deriche
In this paper, we propose to overcome one of the limitations of No Reference (NR) Image Quality Metrics (IQMs). Indeed, this kind of metrics is generally distortion-based and can be used only for a specific degradation such as ringing, blur or blocking. We propose to detect and identify the type of the degradation contained in the image before quantifying its quality. The degradation type is here identified using a Linear Discriminant Analysis (LDA) classifier. Then, the NR-IQM is selected according to the degradation type. We focus our work on the more common artefacts and degradations: blocking, ringing, blur and noise. The efficiency of the proposed method is evaluated in terms of correct classification across the considered degradations and artefacts.
{"title":"A new scheme for no reference image quality assessment","authors":"A. Chetouani, Azeddine Beghdadi, A. Bouzerdoum, Mohamed Deriche","doi":"10.1109/IPTA.2012.6469534","DOIUrl":"https://doi.org/10.1109/IPTA.2012.6469534","url":null,"abstract":"In this paper, we propose to overcome one of the limitations of No Reference (NR) Image Quality Metrics (IQMs). Indeed, this kind of metrics is generally distortion-based and can be used only for a specific degradation such as ringing, blur or blocking. We propose to detect and identify the type of the degradation contained in the image before quantifying its quality. The degradation type is here identified using a Linear Discriminant Analysis (LDA) classifier. Then, the NR-IQM is selected according to the degradation type. We focus our work on the more common artefacts and degradations: blocking, ringing, blur and noise. The efficiency of the proposed method is evaluated in terms of correct classification across the considered degradations and artefacts.","PeriodicalId":267290,"journal":{"name":"2012 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125044635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：