Proceedings ArticleDOI
Texture image classification using pixel N-grams
Pradnya Kulkami,Andrew Stranieri,Julien Ugon +2 more
- pp 137-141
TLDR
Experiments on the benchmark texture database demonstrates that the overall classification accuracy resulting from Pixel N-gram approach is comparable with that achieved using BoVW approach with the added advantage of simplicity and reduced computational cost.Abstract:
Various statistical methods such as co-occurrence matrix, local binary patterns and spectral approaches such as Gabor filters have been used for generating global features for image classification. However, global image features fail to distinguish between local variations within an image. Bag-of-visual-words (BoVW) model do capture local variations in an image, but typically do not consider spatial relationships between the visual words. Here, a novel image representation ‘Pixel N-grams’, inspired from the character N-gram concept in text retrieval has been applied for texture classification purpose. Texture is an important property for image classification. Experiments on the benchmark texture database (UIUC) demonstrates that the overall classification accuracy resulting from Pixel N-gram approach (89.5%) is comparable with that achieved using BoVW approach (84.4%) with the added advantage of simplicity and reduced computational cost.read more
Citations
More filters
Journal ArticleDOI
N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution
TL;DR: NGramSwin this paper introduces the N-Gram context to the low-level vision with Transformers for the first time, which differs from text analysis that views N-gram as consecutive characters or words.
Book ChapterDOI
Pixel N-Grams Representation for Medical Image Classification
TL;DR: A novel feature extraction and image representation technique ‘Pixel N-grams’ inspired from ‘Character N-rams’ concept in text categorization is described in this chapter, demonstrating promising classification accuracy in addition to reduced computational costs, enabling a new way for mammographic classification on low resource computers.
Fine Grained Classification of Mammographic Lesions using Pixel N-grams
TL;DR: It was observed that the classification performance increases with increase in N and then starts decreasing again, and classification performance achieved using MLP classifier was better than the performance using SVM or KNN classifiers.
Proceedings ArticleDOI
Comparison of Pixel N-Grams with Histogram, Haralick's features and Bag-of-Visual-Words for Texture Image Classification
TL;DR: The classification results using Pixel N-gram were significantly better than that using Intensity histogram and Haralick features whereas.
Proceedings ArticleDOI
Pixel N-grams for mammographic lesion classification
TL;DR: A novel Pixel N- gram approach inspired from character N-grams in the text retrieval context has been applied for mammographic lesion classification and results show that optimum value of N is equal to 3 and MLP classifier performs better than SVM and KNN classifier using 3-gram features.
References
More filters
Journal ArticleDOI
Textural Features for Image Classification
TL;DR: These results indicate that the easily computable textural features based on gray-tone spatial dependancies probably have a general applicability for a wide variety of image-classification applications.
Proceedings ArticleDOI
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
TL;DR: This paper presents a method for recognizing scene categories based on approximate global geometric correspondence that exceeds the state of the art on the Caltech-101 database and achieves high accuracy on a large database of fifteen natural scene categories.
Proceedings Article
Visual categorization with bags of keypoints
TL;DR: This bag of keypoints method is based on vector quantization of affine invariant descriptors of image patches and shows that it is simple, computationally efficient and intrinsically invariant.
Journal ArticleDOI
A survey of image classification methods and techniques for improving classification performance
Dengsheng Lu,Qihao Weng +1 more
TL;DR: It is suggested that designing a suitable image‐processing procedure is a prerequisite for a successful classification of remotely sensed data into a thematic map and the selection of a suitable classification method is especially significant for improving classification accuracy.
Journal ArticleDOI
An Evaluation of Statistical Approaches to Text Categorization
TL;DR: Analysis and empirical evidence suggest that the evaluation results on some versions of Reuters were significantly affected by the inclusion of a large portion of unlabelled documents, mading those results difficult to interpret and leading to considerable confusions in the literature.
Related Papers (5)
Texture segmentation based on features in wavelet domain for image retrieval
Ying Liu,Si Wu,Xiaofang Zhou +2 more