We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Deep Learning Based Compression with Classification Model on CMOS Image Sensors.
- Authors
Palani, Vinayagam; Thanarajan, Tamilvizhi; Krishnamurthy, Anand; Rajendran, Surendran
- Abstract
The complementary metal oxide semiconductor (CMOS) technique is widely used in modern manufacturing processes for the high compatibility. A novel metaheuristic with deep learning based compression with image classification model (MDL-CCIM) technique is developing to compress and classify the images captured by CMOS image sensors. The proposed MDL-CCIM technique follows two major processes, namely, butterfly compression and classification. Primarily, the BOA with LBG model is applied for image compression. Secondly, the DenseNet with softmax layer is employed for image classification. Finally, the hyper parameter tuning of the DenseNet model is optimally chosen by the Adam optimizer. A wide range of simulations was carried out to highlight the enhancement of the MDL-CCIM technique. The extensive comparative analysis reported the improved outcomes of the MDL-CCIM technique over the recent approaches. Hybrid DL models can be used for image classification purposes.
- Subjects
DEEP learning; CMOS image sensors; IMAGE recognition (Computer vision); COMPLEMENTARY metal oxide semiconductors; IMAGE compression
- Publication
Traitement du Signal, 2023, Vol 40, Issue 3, p1163
- ISSN
0765-0019
- Publication type
Article
- DOI
10.18280/ts.400332