Texture Image Classification Using DWT AlexNet Feature Fusion and Deep Neural Networks
2026-08-28 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors explain that recognizing textures in images is important for many computer tasks like medical scans and identifying objects. Traditional methods use hand-designed features to spot simple patterns, but they might miss more complex details. On the other hand, deep learning models can learn features automatically but sometimes don't capture texture details at different scales well. To fix this, the authors created a new method that combines wavelet transform features with deep features from a model called AlexNet. This hybrid approach aims to improve how textures are classified in images.
Texture Image ClassificationDiscrete Wavelet Transform (DWT)AlexNetDeep LearningFeature ExtractionHandcrafted FeaturesMultiscale Spatial-FrequencyDeep Neural Network (DNN)
Authors
Arun D. Kulkarni
Abstract
Texture image classification plays a significant role in computer vision applications, including industrial inspection, medical image analysis, remote sensing, and object recognition. Handcrafted features can capture local texture characteristics but may have limited capability to represent complex visual patterns. In contrast, deep learning models automatically learn discriminative representations but may not fully exploit the multiscale spatial-frequency information inherent in texture images. This paper proposes a hybrid feature fusion framework, termed DWT_AlexNet_DNN, which combines Discrete Wavelet Transform (DWT) features with deep features extracted using AlexNet for texture image classification.