Features extraction for image identification using computer vision

📅 2025-07-22
📈 Citations: 0
Influential: 0
📄 PDF

career value

210K/year
🤖 AI Summary
This study systematically evaluates feature extraction methods for image recognition, focusing on Vision Transformers (ViTs) versus traditional handcrafted features (SIFT/SURF/ORB), CNNs, GANs, and deep feature models. Methodologically, we establish a unified experimental framework comparing both non-contrastive and contrastive learning paradigms, incorporating patch embedding, multi-head self-attention, positional encoding, and self-supervised strategies for feature modeling. Our key contributions are: (i) the first empirical demonstration across multiple benchmarks that ViTs—leveraging global contextual modeling—significantly outperform CNNs and handcrafted features in generalization, few-shot adaptation, and cross-domain transfer; and (ii) evidence that contrastive learning further enhances the discriminative power of ViT-derived features. The results provide a reproducible benchmark analysis and principled guidance for architecture selection in visual representation learning.

Technology Category

Application Category

📝 Abstract
This study examines various feature extraction techniques in computer vision, the primary focus of which is on Vision Transformers (ViTs) and other approaches such as Generative Adversarial Networks (GANs), deep feature models, traditional approaches (SIFT, SURF, ORB), and non-contrastive and contrastive feature models. Emphasizing ViTs, the report summarizes their architecture, including patch embedding, positional encoding, and multi-head self-attention mechanisms with which they overperform conventional convolutional neural networks (CNNs). Experimental results determine the merits and limitations of both methods and their utilitarian applications in advancing computer vision.
Problem

Research questions and friction points this paper is trying to address.

Compare feature extraction techniques in computer vision
Analyze Vision Transformers' architecture and performance
Evaluate applications of ViTs and CNNs
Innovation

Methods, ideas, or system contributions that make the work stand out.

Uses Vision Transformers for feature extraction
Compares ViTs with CNNs and GANs
Analyzes patch embedding and self-attention
🔎 Similar Papers
No similar papers found.
V
Venant Niyonkuru
Department of Computing and Information System, Kenyatta University, Kenya
S
Sylla Sekou
Department of Mathematics, Institute for Basic Science, Technology and Innovation, Pan-African University, Kenya
J
Jimmy Jackson Sinzinkayo
Department of Software Engineering, College of Software, Nankai University, China