Filters








22,943 Hits in 3.9 sec

Local Color Contrastive Descriptor for Image Classification [article]

Sheng Guo and Weilin Huang and Yu Qiao
2015 arXiv   pre-print
In this paper, we present a simple yet efficient local descriptor for image classification, referred as Local Color Contrastive Descriptor (LCCD), by leveraging the neural mechanisms of color contrast.  ...  The color contrast is computed by measuring f-divergence between the color distributions of two regions. Our descriptor enriches local image representation with both color and contrast information.  ...  CONCLUSIONS We have presented a simple yet powerful local descriptor, local color contrastive descriptor (LCCD), for image classification.  ... 
arXiv:1508.00307v1 fatcat:fkybrhzfyfeldlrs3c5on425ry

Illuminant Invariant Descriptors for Color Texture Classification [chapter]

Claudio Cusano, Paolo Napoletano, Raimondo Schettini
2013 Lecture Notes in Computer Science  
In this paper we present a novel descriptor for color texture analysis specially designed to deal with changes in illumination in imaging.  ...  The descriptor, that we called Intensity Color Contrast Descriptor (ICCD), is based on a combination of the LBP approach with a measure of color contrast defined as the angle between two color vectors  ...  In this paper we present the Intensity Color Contrast Descriptor (ICCD): a descriptor that combines the Local Binary Pattern approach with information related to the local color contrast of the image.  ... 
doi:10.1007/978-3-642-36700-7_19 fatcat:sbxxathvcnbvpp2qxo44b5jzbi

Color Independent Components Based SIFT Descriptors for Object/Scene Classification

Dan-ni AI, Xian-hua HAN, Xiang RUAN, Yen-wei CHEN
2010 IEICE transactions on information and systems  
The ICA-based color transformation can enhance contrast between the objects and the background in an image.  ...  In this paper, we present a novel color independent components based SIFT descriptor (termed CIC-SIFT) for object/scene classification.  ...  It can enhance contrast between object and background in an image. Consequently, the proposed CIC-SIFT can extract more effective and discriminative local features for object/scene classification.  ... 
doi:10.1587/transinf.e93.d.2577 fatcat:kd3zrormgvdzdnomqcpu3v6kym

Classification of weather situations on single color images

Martin Roser, Frank Moosmann
2008 2008 IEEE Intelligent Vehicles Symposium  
The proposed image descriptor clearly outperforms existing descriptors for that task.  ...  We present an approach that is able to distinguish between multiple weather situations based on the classification of single monocular color images, without any additional assumptions or prior knowledge  ...  For that reason, we used a non-linear RBF kernel for subsequent evaluation. In section II, we proposed a novel image descriptor for the task of weather classification.  ... 
doi:10.1109/ivs.2008.4621205 fatcat:2fnkkyxsm5f7ddptuqm5mx4bhu

Combining local binary patterns and local color contrast for texture classification under varying illumination

Claudio Cusano, Paolo Napoletano, Raimondo Schettini
2014 Optical Society of America. Journal A: Optics, Image Science, and Vision  
The descriptor combines a histogram of local binary patterns (LBPs) with a novel feature measuring the distribution of local color contrast.  ...  This paper presents a texture descriptor for color texture classification specially designed to be robust against changes in the illumination conditions.  ...  In this paper we present a texture descriptor that properly combines a histogram of LBPs with a feature encoding the distribution of local color contrast (LCC).  ... 
doi:10.1364/josaa.31.001453 pmid:25121431 fatcat:cfgibyfbyjcxlh5m3jddikpf2u

F-divergence based local contrastive descriptor for image classification

Sheng Guo, Weilin Huang, Chunjing Xu, Yu Qiao
2014 2014 4th IEEE International Conference on Information Science and Technology  
This paper proposes a novel local contrastive descriptor for image classification based on the f -divergence, referred as LCD.  ...  It extracts local image feature by computing the contrastive characteristic between image patches.  ...  In this work, we propose a novel local contrastive descriptor by effectively leveraging the advantages of the fdivergence for encoding local color information.  ... 
doi:10.1109/icist.2014.6920594 fatcat:dc3uyv4brbdalnghckjapxh3u4

A comparative study of computational aesthetics

Dogancan Temel, Ghassan AlRegib
2014 2014 IEEE International Conference on Image Processing (ICIP)  
Objective metrics model image quality by quantifying image degradations or estimating perceived image quality.  ...  In this paper, we examine computational aesthetics models that use hand-crafted, generic and hybrid descriptors.  ...  Hybrid Descriptors Color, geometric and aesthetics descriptors analyze the images in different aspects and they can be complementary to each other for classification.  ... 
doi:10.1109/icip.2014.7025118 dblp:conf/icip/TemelA14 fatcat:3pxirzikh5bcjgwbfkzmqfbnci

Noise Resilient Local Gradient Orientation for Content-Based Image Retrieval

Samina Bilquees, Hassan Dawood, Hussain Dawood, Nadeem Majeed, Ali Javed, Muhammad Tariq Mahmood, E. Bernabeu
2021 International Journal of Optics  
The proposed NRLGO consists of three steps: estimation and removal of noise to protect the local visual structure; extraction of color, texture, and local contrast features; and, at the end, generation  ...  of microstructure for visual representation.  ...  NRLGO relies on noise removal, color, texture classifications, and local contrast information.  ... 
doi:10.1155/2021/4151482 fatcat:yceevct6nfchvjhztfzquv2loi

Novel chromaticity similarity based color texture descriptor for digital pathology image analysis

Xingyu Li, Konstantinos N Plataniotis
2018 PLoS ONE  
Aware of the high color diagnosticity in pathology images, this work introduces a compact rotation-invariant texture descriptor, named quantized diagnostic counter-color pattern (QDCP), for digital pathology  ...  On the basis of color similarity quantified by the inner product of unit-length color vectors, local counter-color textons are indexed first.  ...  LCC-LBP combines the local contrast histogram to LBP descriptor extracted from the image luma component [30] .  ... 
doi:10.1371/journal.pone.0206996 pmid:30419049 pmcid:PMC6231632 fatcat:x5rfoaiywrapje7udjhcdd75wu

Assessing the aesthetic quality of photographs using generic image descriptors

Luca Marchesotti, Florent Perronnin, Diane Larlus, Gabriela Csurka
2011 2011 International Conference on Computer Vision  
We depart from this line of research and propose to use generic image descriptors to assess aesthetic quality.  ...  We experimentally show that the descriptors we use, which aggregate statistics computed from low-level local features, implicitly encode the aesthetic properties explicitly used by state-of-the-art methods  ...  In contrast, images with too many colors, or cheerless colors, received low scores.  ... 
doi:10.1109/iccv.2011.6126444 dblp:conf/iccv/MarchesottiPLC11 fatcat:y5nom5t5a5d3fgr44b2wiqewra

Aggregated color descriptors for land use classification

Vedran Jovanovic, Vladimir Risojevic
2015 Telfor Journal  
In this paper we propose and evaluate aggregated color descriptors for land use classification in aerial images.  ...  First, global and local Bag-of-Colors (BoC) descriptors are evaluated for land use classification. Influence of different parameters on the performance and efficiency of classification were tested.  ...  In [9] the Bag-of-Colors (BoC) descriptor has been introduced that uses an adaptive approach for color codebook computation, in contrast to fixed color partition, traditionally used with color descriptors  ... 
doi:10.5937/telfor1502091j fatcat:v3dsn2ekg5b3xlchzkccb6xs6y

Evaluating color texture descriptors under large variations of controlled lighting conditions

Claudio Cusano, Paolo Napoletano, Raimondo Schettini
2015 Optical Society of America. Journal A: Optics, Image Science, and Vision  
Several features have been proposed for this purpose, ranging from traditional statistical descriptors to features extracted with neural networks.  ...  The database allows to systematically investigate the robustness of texture descriptors across a large range of variations of imaging conditions.  ...  on pairs of color channels, namely the Opponent Color LBP (OCLBP) [50] ; • LBP combined with the Local Color Contrast descriptor, as described in [37] ; • 499-dimensional Local Color Contrast feature  ... 
doi:10.1364/josaa.33.000017 pmid:26831581 fatcat:kqijvzwbvbgdvar7mtr63cysvy

Assorted Techniques for Defining Image Descriptors to Augment Content Based Classification Accuracy

2020 International Journal of Engineering and Advanced Technology  
The three different feature vectors feature vector are contrasted to investigate the robustness of descriptor definition for content based image classification  ...  Content based image classification (CBIC) thus gained it's popularity in classifying images to their corresponding categories.  ...  Defining Descriptor using Image Binarization A local threshold based technique named Bernse's local threshold selection is used for adaptive binarization of images and separating the area of interest for  ... 
doi:10.35940/ijeat.b4208.029320 fatcat:jwe6bb5ymbgjdhmqzssuhzpogm

Local Angular Patterns for Color Texture Classification [chapter]

Claudio Cusano, Paolo Napoletano, Raimondo Schettini
2015 Lecture Notes in Computer Science  
We defined a new color texture descriptor, that we called Local Angular Patterns, specially designed to be robust to changes in the color of the illuminant.  ...  The results show that our descriptor outperforms the state-of-the-art on a dataset of food textures.  ...  To this purpose, we proposed a new descriptor that exploits a novel color space transformation and a novel descriptor based on Local Angular Patterns.  ... 
doi:10.1007/978-3-319-23222-5_14 fatcat:2vs2nqw6xvhetdylfwcsfvpu4u

Local Intensity Ordering based Binary Patterns for Image Region Description

Rajkumar Kannan, Suresh Kannaiyan
2017 Advances In Image and Video Processing  
Local image region description is a fundamental task for image feature matching in the field of Computer Vision.  ...  In this paper, two novel local image region descriptors called Local Intensity Order-based Center Symmetric Local Binary Patterns (LIOCSLBP) and Local Intensity Order-based Orthogonally Combined Local  ...  The proposed color descriptor LIOCSLBP presents best performance in scene classification for OT scene dataset.  ... 
doi:10.14738/aivp.53.3279 fatcat:rypreie43jdkzpzdfgu7ftjmmq
« Previous Showing results 1 — 15 out of 22,943 results