Rama Krishna Gorthi

Indian Institute of Technology Tirupati

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Deepak Mishra

Indian Institute of Space Science and Technology

Subrahmanyam Gorthi

Indian Institute of Technology Tirupati

Mohana Murali Dasari

Indian Institute of Technology Tirupati

G. Gopakumar

Amrita Vishwa Vidyapeetham

Michael Felsberg

Linköping University

Roman Pflugfelder

Austrian Institute of Technology

Sai Siva Gorthi

Indian Institute of Science Bangalore

Gustavo J. Fernández

National University of Comahue

Alireza Memarmoghadam

University of Isfahan

Huchuan Lu

Dalian University of Technology

Cooperative Institutions

Chinese Academy of Sciences

110

University of Chinese Academy of Sciences

Dalian University of Technology

Indian Institute of Space Science and Technology

Indian Institute of Technology Tirupati

Shanghai Jiao Tong University

Zhejiang University

Tsinghua University

Huazhong University of Science and Technology

University of Science and Technology of China

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Towards Automated Breast Mass Classification using Deep Learning Framework

Pinaki Ranjan Sarkar Priya Prabhakar Deepak Mishra Rama Krishna Gorthi

Due to high variability in shape, structure and occurrence; the non-palpable breast masses are often missed by the experienced radiologists. To aid them with more accurate identification, computer-aided detection (CAD) systems are widely used. Most of the developed CAD systems use complex handcrafted features which introduce difficulties for further improvement in performance. Deep or high-level features extracted using deep learning models already have proven its superiority over the low or middle-level handcrafted features. In this paper, we propose an automated deep CAD system performing both the functions: mass detection and classification. Our proposed framework is composed of three cascaded structures: suspicious region identification, mass/no-mass detection and mass classification. To detect the suspicious regions in a breast mammogram, we have used a deep hierarchical mass prediction network. Then we take a decision on whether the predicted lesions contain any abnormal masses using CNN high-level features from the augmented intensity and wavelet features. Afterwards, the mass classification is carried out only for abnormal cases with the same CNN structure. The whole process of breast mass classification including the extraction of wavelet features is automated in this work. We have tested our proposed model on widely used DDSM and INbreast databases in which mass prediction network has achieved the sensitivity of 0.94 and 0.96 followed by a mass/no-mass detection with the area under the curve (AUC) of 0.9976 and 0.9922 respectively on receiver operating characteristic (ROC) curve. Finally, the classification network has obtained an accuracy of 98.05% in DDSM and 98.14% in INbreast database which we believe is the best reported so far.

Identification

10.1109/dsaa.2019.00060

Cite

Citations (9)

Bayesian Approach for Landslide Identification from High-Resolution Satellite Images

Advances in intelligent systems and computing (2018)

Pilli Madalasa Rama Krishna Gorthi Tapas R. Martha ‪Rama Rao Nidamanuri Deepak Mishra

Identification

10.1007/978-981-10-7898-9_2

Cite

Citations (1)

Batch-Mode Active Learning-Based Superpixel Library Generation for Very High-Resolution Aerial Image Classification

Advances in intelligent systems and computing (2018)

Rajeswari Balasubramaniam Srivalsan Namboodiri Rama Krishna Gorthi ‪Rama Rao Nidamanuri

Softmax function

Contextual image classification

10.1007/978-981-13-1135-2_24

Cite

Citations (0)

NSSR-DIL: Null-Shot Image Super-Resolution Using Deep Identity Learning

arXiv (Cornell University) (2024)

Sree Rama Vamsidhar S Rama Krishna Gorthi

The present State-of-the-Art (SotA) Image Super-Resolution (ISR) methods employ Deep Learning (DL) techniques using a large amount of image data. The primary limitation to extending the existing SotA ISR works for real-world instances is their computational and time complexities. In this paper, contrary to the existing methods, we present a novel and computationally efficient ISR algorithm that is independent of the image dataset to learn the ISR task. The proposed algorithm reformulates the ISR task from generating the Super-Resolved (SR) images to computing the inverse of the kernels that span the degradation space. We introduce Deep Identity Learning, exploiting the identity relation between the degradation and inverse degradation models. The proposed approach neither relies on the ISR dataset nor on a single input low-resolution (LR) image (like the self-supervised method i.e. ZSSR) to model the ISR task. Hence we term our model as Null-Shot Super-Resolution Using Deep Identity Learning (NSSR-DIL). The proposed NSSR-DIL model requires fewer computational resources, at least by an order of 10, and demonstrates a competitive performance on benchmark ISR datasets. Another salient aspect of our proposition is that the NSSR-DIL framework detours retraining the model and remains the same for varying scale factors like X2, X3, and X4. This makes our highly efficient ISR model more suitable for real-world applications.

Null (SQL)

Single shot

10.48550/arxiv.2409.12165

Cite

Citations (0)

IG-TRACK: IOU Guided Siamese Networks for visual object tracking

arXiv (Cornell University) (2020)

Mohana Murali Dasari Rama Krishna Gorthi

Recently Deep Learning based Siamese Networks with region proposals for visual object tracking becoming more popular. These networks, while testing, perform extra computations on output if trained network, to predict the bounding box. This however hampering the precision of bounding box. In this work, the authors have proposed a network guided by Intersection Over Union(IOU) while training, to predict precise bounding box. This is achieved by adding new loss function in training the network, to maximize IOU of the predicted bounding box with ground truth. While testing on VOT2018, GOT-10k tracking benchmarks,the proposed approach out-performed the base approach by more than 10% in terms of precision.

Minimum bounding box

Bounding overwatch

Ground truth

Tracking (education)

Black box

10.48550/arxiv.2001.09307

Cite

Citations (0)

OSVFuseNet: Online Signature Verification by feature fusion and depth-wise separable convolution based deep learning

Neurocomputing (2020)

Chandra Sekhar Vorugunti P. Viswanath Rama Krishna Gorthi Prerana Mukherjee

Signature (topology)