Special Issue "Color Texture Classification"
A special issue of Journal of Imaging (ISSN 2313-433X).
Deadline for manuscript submissions: 31 October 2021.
Interests: color representation; color and hypespectral imaging; dimensionality reduction; feature selection; texture classification; image segmentation; machine vision applications
Texture and color are salient visual cues in human perception and color textures provide essential information for object recognition and scene understanding. Therefore, color texture analysis is widely used in many imaging applications and color texture classification continues to be an active research topic which has seen major advances due to the emergence of deep learning in recent decades. In this context, color texture descriptors have evolved from "handcrafted" descriptors which provide color texture features based on manually defined models into "learned" descriptors which are directly designed from image data. Well-known classifiers or their combination have given way to convolutional neural networks (CNN) and pre-trained CNN. Although these deep learning and transfer models provide impressive performance, the representations generated can be difficult to understand and they suffer from their dependence on training data.
When the generated color texture features produce high-dimensional representations, bag-of-words strategies, feature selection approaches, or pooling stages are needed to reduce the dimensionality of these big data. The key challenge of color texture classification is to ensure high classification accuracy with low computation times despite a potentially large number of texture classes, high intra-class and low inter-class appearance variations of the texture, and limited training data.
The choice or the combination of different texture descriptors, color spaces, or classifiers and the integration of handcrafted descriptors into the design of deep learning models as well as the suitable adjustment of their parameters to produce interpretable, flexible, robust, invariant, and compact descriptors for color texture classification are all existing problems which remain unaddressed.
This Special Issue aims to present recent theoretical and practical advances in the field of color texture classification for researchers and practitioners, including new approaches, challenging applications, and future perspectives. Original contributions, state-of-the-art surveys, and comprehensive comparative reviews are welcome.
Dr. Nicolas Vandenbroucke
Dr. Alice Porebski
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Imaging is an international peer-reviewed open access monthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
- color texture representation
- color spaces
- hand-designed descriptor
- deep learning and hybrid approaches
- dimensionality reduction
- comparative evaluations and benchmarks