no code implementations • 11 Aug 2023 • Bulla Rajesh, Sk Mahafuz Zaman, Mohammed Javed, P. Nagabhushan
Automatic localization of text-lines in handwritten documents is still an open and challenging research problem.
no code implementations • 1 Oct 2022 • Bulla Rajesh, Nandakishore Dusa, Mohammed Javed, Shiv Ram Dubey, P. Nagabhushan
The first model is directly trained with JPEG compressed DCT images (compressed domain) to generate the compressed images from text descriptions.
no code implementations • 13 Sep 2022 • Bulla Rajesh, Manav Kamlesh Agrawal, Milan Bhuva, Kisalaya Kishore, Mohammed Javed
Image binarization techniques are being popularly used in enhancement of noisy and/or degraded images catering different Document Image Anlaysis (DIA) applications like word spotting, document retrieval, and OCR.
no code implementations • 4 Jan 2022 • Bulla Rajesh, Abhishek Kumar Gupta, Ayush Raj, Mohammed Javed, Shiv Ram Dubey
Handwritten word recognition from document images using deep learning is an active research area in the field of Document Image Analysis and Recognition.
no code implementations • 10 Jul 2021 • Atul Sharma, Bulla Rajesh, Mohammed Javed
Therefore accurate and timely detection of leaf disease is very important to check the loss of the crops and meet the growing food demand of the people.
no code implementations • 8 Jul 2021 • Shrikant Temburwar, Bulla Rajesh, Mohammed Javed
Here, we propose a unified model for image retrieval which takes DCT coefficients as input and efficiently extracts global and local features directly in the JPEG compressed domain for accurate image retrieval.
no code implementations • 29 Jul 2019 • Bulla Rajesh, Mohammed Javed, P. Nagabhushan
The first approach is based on the strategy of partial decompression of selected DCT blocks, and the second approach is with intelligent analysis of F10 and F11 AC coefficients and without using any type of decompression.
no code implementations • 26 Jul 2019 • Bulla Rajesh, Mohammed Javed, Ratnesh, Shubham Srivastava
However, if we intend to classify images directly with its compressed data, the same approach may not work better, like in case of JPEG compressed images.