Abstract
Colour and texture are two perceptual stimuli that determine, to a great extent, the appearance of objects, materials and scenes. The ability to process texture and colour is a fundamental skill in humans as well as in animals; therefore, reproducing such capacity in artificial (‘intelligent’) systems has attracted considerable research attention since the early 70s. Whereas the main approach to the problem was essentially theory-driven (‘hand-crafted’) up to not long ago, in recent years the focus has moved towards data-driven solutions (deep learning). In this overview we retrace the key ideas and methods that have accompanied the evolution of colour and texture analysis over the last five decades, from the ‘early years’ to convolutional networks. Specifically, we review geometric, differential, statistical and rank-based approaches. Advantages and disadvantages of traditional methods vs. deep learning are also critically discussed, including a perspective on which traditional methods have already been subsumed by deep learning or would be feasible to integrate in a data-driven approach.
Highlights
The Psychology Dictionary gives two definitions of visual recognition: (a) ‘the capacity to identify an item visually’ and (b) ‘the ability to recognize items in their visual environment’ [1]; while visual, according to the Oxford English Dictionary, means ‘related to seeing or sight’ [2]
The results reported in [88] demonstrate that the image patch-based classifier (IPBC) is as effective as BoVW implementations based on filter responses
In the following subsections we briefly review the basic layer types, the main convolutional neural networks (CNN) architectures and discuss the usage for colour texture classification
Summary
The Psychology Dictionary gives two definitions of visual recognition: (a) ‘the capacity to identify an item visually’ and (b) ‘the ability to recognize items in their visual environment’ [1]; while visual, according to the Oxford English Dictionary, means ‘related to seeing or sight’ [2]. Colour and texture play a central role in this context: the ability to process these stimuli is one of the fundamental skills that enable humans to interact effectively with the environment they live in. Reproducing this capacity in artificial systems has been a hot topic in computer vision since early on. The objective of this note is to review the main concepts behind colour and texture descriptors from a historical perspective. Our approach is diachronic and synchronic at the same time: while our perspective is mostly historical, we provide a taxonomy of the available methods and underline the key differences among them
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.