Undi Surya Narayana Raju
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Undi Surya Narayana Raju has a total of 88 co-authors. Here are the top co-authors by number of shared publications:
- Mahesh Kumar Morampudi
SRM University-AP
5 shared publications - Chilakala Shanthi
National Institute of Technology
4 shared publications - Debanjan Pathak
National Institute of Technology Warangal
4 shared publications Munaga V. N. K. Prasad
Institute for Development and Research in Banking Technology (IDRBT) Hyderabad India
4 shared publications- Sweta Panigrahi
National Institute of Technology Warangal
4 shared publications Hillol Barman
National Institute of Technology Warangal
3 shared publications
Latest Publications
- 1 May 2026
- Published by Springer Nature
- p. 221-231
Quantifying Noise Levels in Images Using a Hybrid Efficient-Inception Model
- 1 May 2026
- Published by Springer Nature
- p. 221-231
Quantifying Noise Levels in Images Using a Hybrid Efficient-Inception Model
- 1 May 2026
- Published by Springer Nature
- p. 212-220
Estimating Impulse Noise Level Using Local Similarity of Adaptive Threshold
- 1 May 2026
- Published by Springer Nature
- p. 212-220
Estimating Impulse Noise Level Using Local Similarity of Adaptive Threshold
- 6 December 2024
- Published by Springer Nature
- p. 299-307
Single Image Super-Resolution Evaluated Using Objective Metrics
- 6 December 2024
- Published by Springer Nature
- p. 299-307
Single Image Super-Resolution Evaluated Using Objective Metrics
- 5 December 2024
- Published by Springer Nature
- p. 185-196
Deep Learning for Digital Olfaction: Graph-Based Self-Supervised Learning
- 5 December 2024
- Published by Springer Nature
- p. 185-196
Deep Learning for Digital Olfaction: Graph-Based Self-Supervised Learning
- 5 December 2024
- Published by Springer Nature
- p. 209-221
Autoencoder-Huffman Ensemble Model for Image Compression
- 5 December 2024
- Published by Springer Nature
- p. 209-221
Autoencoder-Huffman Ensemble Model for Image Compression
- 8 November 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (17) , 50783-50823
Distributed compression and decompression for big image data: JPEG and CCITT Group-3
- 8 November 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (17) , 50783-50823
Distributed compression and decompression for big image data: JPEG and CCITT Group-3
- 30 June 2023
- Published by World Scientific Pub Co Pte Ltd in International Journal on Artificial Intelligence Tools
- Vol. 32 (04)
DSM-IDM-YOLO: Depth-wise Separable Module and Inception Depth-wise Module Based YOLO for Pedestrian Detection
Pedestrian detection is one of the most challenging research areas in computer vision. Compared to traditional hand-crafted methods, convolutional neural networks (CNNs) have superior detection results. The single-stage detection networks, particularly the state-of-the-art You Only Look Once (YOLO) network, have attained a satisfactory performance without compromising the computation speed in object detection. YOLO framework can be leveraged in pedestrian detection as well. In this work, we propose an improved YOLOv2, called DSM-IDM-YOLO. The proposed model uses a modified DarkNet19 integrated with three new modules, two depth-wise separable convolution modules and one inception depth-wise convolution module, leading to a comprehensive feature of an object in the image. The modules are integrated on top of features from multiple levels of the network. The proposed framework is computationally less expensive owing to its convolution design and a moderate number of layers. It aims to improve performance with minimal computational overhead. The proposed method is compared with state-of-the-art detection methods, i.e., Faster R-CNN, YOLOv2, YOLOv3, YOLOv4-tiny and Single Shot Multibox Detector (SSD). The performance results attest that the proposed method has effectively improved the detection. Three benchmark pedestrian datasets are used for experimental analysis: INRIA, PASCAL VOC 2012 and Caltech.
- 30 June 2023
- Published by World Scientific Pub Co Pte Ltd in International Journal on Artificial Intelligence Tools
- Vol. 32 (04)
DSM-IDM-YOLO: Depth-wise Separable Module and Inception Depth-wise Module Based YOLO for Pedestrian Detection
Pedestrian detection is one of the most challenging research areas in computer vision. Compared to traditional hand-crafted methods, convolutional neural networks (CNNs) have superior detection results. The single-stage detection networks, particularly the state-of-the-art You Only Look Once (YOLO) network, have attained a satisfactory performance without compromising the computation speed in object detection. YOLO framework can be leveraged in pedestrian detection as well. In this work, we propose an improved YOLOv2, called DSM-IDM-YOLO. The proposed model uses a modified DarkNet19 integrated with three new modules, two depth-wise separable convolution modules and one inception depth-wise convolution module, leading to a comprehensive feature of an object in the image. The modules are integrated on top of features from multiple levels of the network. The proposed framework is computationally less expensive owing to its convolution design and a moderate number of layers. It aims to improve performance with minimal computational overhead. The proposed method is compared with state-of-the-art detection methods, i.e., Faster R-CNN, YOLOv2, YOLOv3, YOLOv4-tiny and Single Shot Multibox Detector (SSD). The performance results attest that the proposed method has effectively improved the detection. Three benchmark pedestrian datasets are used for experimental analysis: INRIA, PASCAL VOC 2012 and Caltech.
- 1 January 2023
- Published by Springer Nature
- p. 19-27
Distributed Deep Learning for Content-Based Image Retrieval
- 1 January 2023
- Published by Springer Nature
- p. 19-27
Distributed Deep Learning for Content-Based Image Retrieval
- 11 May 2022
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 11 (3) , 409-430
InceptionDepth-wiseYOLOv2: improved implementation of YOLO framework for pedestrian detection
- 11 May 2022
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 11 (3) , 409-430
InceptionDepth-wiseYOLOv2: improved implementation of YOLO framework for pedestrian detection
- 28 January 2022
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 34 (22) , e6851
Content‐based image retrieval for super‐resolutioned images using feature fusion: Deep learning and hand crafted
An innovative image retrieval agenda by concatenating deep learning features from GoogleNet and low‐level features from HSI and RGB color space is proposed in this article. Most of the CNN features suffer from loss of information due to image resize as a pre‐processing stage. To reduce this information loss super‐resolution technic is used for resizing images. An improved form of dot‐diffused block truncation coding is used for extracting RGB handcraft features. To discover the interdependencies between color and intensity component of an image, interchannel voting between hue, saturation, and intensity component is calculated as a color feature in HSI space. Histogram of orientated gradient (HOG) feature is used as shape feature. Five standard performance parameters, average precision rate, average recall rate, F‐Measure, Average Normalized Modified Retrieval Rank, and Total Minimum Retrieval Epoch, are applied on nine image datasets: Corel‐1K, Corel‐5K, Corel‐10K, VisTex, STex, ColorBrodatz and three subsets of ImageNet dataset for evaluation process of proposed method. For all dataset the best performance is achieved by the proposed method with respect to all performance parameters.
- 28 January 2022
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 34 (22) , e6851
Content‐based image retrieval for super‐resolutioned images using feature fusion: Deep learning and hand crafted
An innovative image retrieval agenda by concatenating deep learning features from GoogleNet and low‐level features from HSI and RGB color space is proposed in this article. Most of the CNN features suffer from loss of information due to image resize as a pre‐processing stage. To reduce this information loss super‐resolution technic is used for resizing images. An improved form of dot‐diffused block truncation coding is used for extracting RGB handcraft features. To discover the interdependencies between color and intensity component of an image, interchannel voting between hue, saturation, and intensity component is calculated as a color feature in HSI space. Histogram of orientated gradient (HOG) feature is used as shape feature. Five standard performance parameters, average precision rate, average recall rate, F‐Measure, Average Normalized Modified Retrieval Rank, and Total Minimum Retrieval Epoch, are applied on nine image datasets: Corel‐1K, Corel‐5K, Corel‐10K, VisTex, STex, ColorBrodatz and three subsets of ImageNet dataset for evaluation process of proposed method. For all dataset the best performance is achieved by the proposed method with respect to all performance parameters.