We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
A novel technique for image classification using short-time Fourier transform and local binary pattern.
- Authors
Khanna, Ketna; Gambhir, Sapna; Gambhir, Mohit
- Abstract
Machine Learning (ML) has been widely used for Image processing. The pertinent feature extraction and feature selection techniques can help us to accomplish many complex tasks. This paper presents a framework for the classification of emotions using ML. Training and testing have been done using the JAFFE (Japanese Female Facial Expression) dataset. The work proposes a combination of Short-Time Fourier Transform (STFT) and Local Binary Pattern (LBP) for extracting interesting features. Also, a fusion of popular feature reduction techniques namely: Fisher Discriminant Ratio (FDR), variance threshold method and chi-square test has been introduced. The selected relevant features are applied to the Support Vector Machine (SVM) classifier. Performance analysis of the existing techniques and the proposed technique has been carried out where the latter was found efficient. The proposed pipeline performs better in terms of accuracy, specificity and sensitivity as compared to the state of art.
- Subjects
FOURIER transforms; FEATURE selection; FEATURE extraction; SUPPORT vector machines; IMAGE processing
- Publication
Multimedia Tools & Applications, 2022, Vol 81, Issue 15, p20705
- ISSN
1380-7501
- Publication type
Article
- DOI
10.1007/s11042-022-12671-z