Exploiting deep and hand-crafted features for texture image retrieval using class membership

Yelchuri, Rajesh; Dash, Jatindra Kumar; Singh, Priyanka; Mahapatro, Arunanshu; Panigrahi, Sibarama

doi:10.1016/j.patrec.2022.06.017

Cited by 6 publications

(6 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, for some tasks (e.g., classification of images from very small databases, often encountered in the medical field), the use of deep learning is excessive and the size of the database will be insufficient to train the model. The future would perhaps be to aggregate descriptors resulting from the combination of hand-crafted methods and deep learning ones, as recently proposed [ 39 , 40 ].…”

Section: Results and Discussionmentioning

confidence: 99%

Deep Learning and Entropy-Based Texture Features for Color Image Classification

Lhermitte

Hilal

Furlong

et al. 2022

Entropy

View full text Add to dashboard Cite

In the domain of computer vision, entropy—defined as a measure of irregularity—has been proposed as an effective method for analyzing the texture of images. Several studies have shown that, with specific parameter tuning, entropy-based approaches achieve high accuracy in terms of classification results for texture images, when associated with machine learning classifiers. However, few entropy measures have been extended to studying color images. Moreover, the literature is missing comparative analyses of entropy-based and modern deep learning-based classification methods for RGB color images. In order to address this matter, we first propose a new entropy-based measure for RGB images based on a multivariate approach. This multivariate approach is a bi-dimensional extension of the methods that have been successfully applied to multivariate signals (unidimensional data). Then, we compare the classification results of this new approach with those obtained from several deep learning methods. The entropy-based method for RGB image classification that we propose leads to promising results. In future studies, the measure could be extended to study other color spaces as well.

show abstract

Section: Results and Discussionmentioning

confidence: 99%

Deep Learning and Entropy-Based Texture Features for Color Image Classification

Lhermitte

Hilal

Furlong

et al. 2022

Entropy

View full text Add to dashboard Cite

show abstract

“…The common framework of CBIR consists of two parts: feature extraction and similarity measurement. The adopted features include hand-crafted features and deep features [3]. Hand-crafted features are artificially designed to characterize different image information, which can be divided into texture, color, and shape features.…”

Section: Introductionmentioning

confidence: 99%

A novel plaid fabric image retrieval method based on hand- crafted features

Zhang,

Zhao,

Ruru

et al. 2024

Preprint

View full text Add to dashboard Cite

Fabric image retrieval can obtain technological parameters of existing similar fabric images to guide production, saving lots of labor and material resources in the proofing process. This paper presents a novel image retrieval method for plaid fabrics based on hand-crafted features. First, local texture descriptors are extracted by the local binary pattern on the separated images which are processed by Fourier transform. Global texture descriptors are extracted by Scale-Invariant Feature Transform (SIFT) and Vector of Locally Aggregated Descriptors (VLAD). Second, color moments with image partitioning are extracted to characterize spatial color information of plaid fabric images. Third, the similarities of the three features are calculated and fused by the weight assignment to realize the plaid fabric image retrieval. To verify the proposed method, over 30,000 plaid fabric samples are collected from the factory to build the image database as the benchmark. Experiments show that precision and recall at rank five reach 70.6% and 62.6%, respectively, and mAP reaches 0.690. Results prove that the proposed method is feasible and effective, which can provide references for the worker and help the fabric manufacturing factory save lots of labor and material resources.

show abstract

“…Recently, several methods have emerged that rely on fuzzy rules [43,44], deep metric learning, and attention mechanisms [45,46], which use the discriminative ability of the deep features of the CNN. Deep metric learning is used in several research areas like natural image retrieval [47], person re-identification [48] and face recognition [49], which has proven to be effective.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, Yelchuri et al [44] proposed an image retrieval system for texture image retrieval which uses the strength of the CNN in calculating the fuzzy class membership of the query image for all the available output classes and uses weighted distance metric to retrieve the images from the wavelet feature space. Apart from this, these fuzzy methods are fully supervised in nature and need the class label information which should be indexed in the database.…”

Section: Introductionmentioning

confidence: 99%

Deep Semantic Feature Reduction for Efficient Remote Sensing Image Retrieval

Yelchuri,

Khadidos,

Khadidos

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

Content-Based Remote Sensing Image Retrieval (CBRSIR) is used to find relevant images from large collections of remote sensing images. CBRSIR works by indexing each image in the database with a feature vector. Deep semantic features generated using convolutional neural networks (CNNs) are more powerful than low-level features for CBRSIR tasks because they can comprehend the context and content within an image. However, the major problem with the deep features is its large vector size which in turn can impact the performance of the retrieval system and are more susceptible to noise and outlier data. Therefore, in this work, a modified ResNet50 architecture is proposed that serves as a powerful feature extractor, benefiting from its deep learning capabilities. Specific modifications are introduced to enhance its discriminative power and generalization ability, enabling it to extract more robust deep features for image indexing. The proposed method achieves a mean average precision (mAP) of 0.899 surpassing the popular competing methods ResNet50 and GoogleNet by a substantial margin of 22.02%, 26.79% respectively. Moreover, to address the curse of dimensionality, this study also proposes a novel approach that combines a modified ResNet50 architecture with Linear Discriminant Analysis (LDA) and Maximum Relevance and Minimum Redundancy (MRMR) technique. The proposed approach achieves 85.45% reduction in size of the feature vector using MRMR and 98.19% using LDA, thereby improving retrieval efficiency without impacting the performance.

show abstract

Exploiting deep and hand-crafted features for texture image retrieval using class membership

Cited by 6 publications

References 25 publications

Deep Learning and Entropy-Based Texture Features for Color Image Classification

Deep Learning and Entropy-Based Texture Features for Color Image Classification

A novel plaid fabric image retrieval method based on hand- crafted features

Deep Semantic Feature Reduction for Efficient Remote Sensing Image Retrieval

Contact Info

Product

Resources

About