Book ChapterDOI
Hand-Crafted vs Learned Descriptors for Color Texture Classification
Paolo Napoletano
- pp 259-271
Reads0
Chats0
TLDR
Results demonstrate that learned descriptors, on average, significantly outperform hand-crafted descriptors for color texture classification, however, results obtained on the individual databases show that in the case of Outex 14, that includes training and test images taken under varying illuminant conditions, hand- crafted descriptors perform better than learning descriptors.Abstract:
The paper presents a comparison between hand-crafted and learned descriptors for color texture classification. The comparison is performed on five color texture databases that include images under varying imaging conditions: scales, camera orientations, light orientations, light color temperatures, etc. Results demonstrate that learned descriptors, on average, significantly outperform hand-crafted descriptors. However, results obtained on the individual databases show that in the case of Outex 14, that includes training and test images taken under varying illuminant conditions, hand-crafted descriptors perform better than learned descriptors.read more
Citations
More filters
Journal ArticleDOI
From BoW to CNN: Two Decades of Texture Representation for Texture Classification
TL;DR: More than 250 major publications are cited in this survey covering different aspects of the research, including benchmark datasets and state-of-the-art results as discussed by the authors, in retrospect of what has been achieved so far and open challenges and directions for future research.
Journal ArticleDOI
Anomaly Detection in Nanofibrous Materials by CNN-Based Self-Similarity.
TL;DR: A region-based method for the detection and localization of anomalies in SEM images, based on Convolutional Neural Networks (CNNs) and self-similarity, which outperforms the state of the art.
Posted Content
From BoW to CNN: Two Decades of Texture Representation for Texture Classification
TL;DR: A comprehensive survey of advances in texture representation over the last two decades is presented covering different aspects of the research, including benchmark datasets and state of the art results.
Journal ArticleDOI
Diabetic retinopathy detection and stage classification in eye fundus images using active deep learning
TL;DR: In this article, an active deep learning (ADL-CNN) model was proposed to automatically extract features compare to handcrafted-based features for diabetic retinopathy (DR) screening.
Journal ArticleDOI
Comparative Evaluation of Hand-Crafted Image Descriptors vs. Off-the-Shelf CNN-Based Features for Colour Texture Classification under Ideal and Realistic Conditions
Raquel Bello-Cerezo,Francesco Bianconi,Francesco Di Maria,Paolo Napoletano,Fabrizio Smeraldi +4 more
TL;DR: Traditional, hand-crafted descriptors were better at discriminating stationary textures under steady imaging conditions and proved more robust than CNN-based features to image rotation, indicating a marked superiority of deep networks with non-stationary textures and in the presence of multiple changes in the acquisition conditions.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Related Papers (5)
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more