Sumaiya

Publications

Enhancement of Resulting Image Search Engine (ERISE) by Content-Based Image Retrieval System

Published in: 2020 IEEE Region 10 Symposium (TENSYMP)

Sumaiya, MD Armanuzzaman

The execution of (ERISE) framework depends on proficient feature extraction and exact recovery of comparative enhancement of resulting images. This paper represents a brief investigation of the main techniques utilized for every image recovery, whereas indicating the importance of this rising innovation. Due to the alarming growth of the Web and the brightly high volume of information, we extend the method of CBIR - Content-Based Image Retrieval system by adding an extra dimension of enhancement. The point of this paper is also to create a framework design to back querying for exceptionally huge image databases with user-specified distance measures that can be utilized for a wide assortment of datasets in the domain of image enhancement. A large number of image query results image retrieval by query image but image quality may affect sometimes. That's why it's much important to enhance the image quality for better usage of an image when needed. The methodology illustrates the authenticity of this current methodology's convenience by differentiating out its efficiency from current methodologies.

Color Correction by QAB (Quantum Particle Swarm Optimization-Ant Colony OptimizationBack Propagation) method

Published in: The 16th International Conference on Computer Science and Education (ICCSE2021)

Sumaiya, MD Armanuzzaman

Now-a-days color correction has been so well accepted method for recovering color information. We proposed a color correction technique based on QPSO- ACO-BP algorithm. Firstly, the QPSO and ACO algorithms are merged. Then the optimized values are retrieved through the merged QPSO-ACO algorithm. BP model is utilized for accomplishing a model regarding this. This model performed with Macbeth Color Checker on the images for color correction. The experimental results show that our proposed technique goes well for color correction. We checked some quality metrics like PSNR (Peak Signal to Noise Ratio) and MSE (Mean Square Error) for the evaluation of results and found the desired improvement.

DURISE- Deblurring of Underwater Image Search Engine by CBIR

Accepted in: 5th International Conference on Electrical Engineering and Information & Communication Technology (ICEEICT)

Sumaiya, MD Armanuzzaman

Content or substance based image recovery (CBIR) has ended up a primary investigate range in interactive media applications. In the literature, there's part of papers centering on the content-based image recovery in arrange to extricate the semantic information inside the inquiry concept. The CBIR strategies utilized in the image looking ranges vary by the user interaction and preparing fashion in inquiry image input. This paper applies the visual location to submerged pictures include extraction to work out the vigor issue, which is conducive to a more steady and closer to human cognitive component include extraction calculation for a better view. In expansion, within the preparation of underwater images pretreatment, we apply dim channel earlier “Deblurring” to the submerged images preprocessing handle to expel cloudiness and improve the differentiate of submerged pictures. The outcomes about moreover appear that the strength and the property of real-time include extraction based on visual saliency discovery and dark picture defogging calculation has been enormously progressed with deblurring the blurred image.

Soft Error Tolerance using Horizontal, Vertical, Diagonal and Seven Queen Parity

Published in: 2019 IEEE International Conference on Signal Processing, Information, Communication & Systems (SPICSCON)

Sumaiya, Mouly Dewan & Muhammad Sheikh Sadi

Soft error is a form of error that has an incorrect signal or datum. It is one of the biggest reliability challenges in the usage of electronic devices and several safety critical applications. In embedded systems, soft errors often cause failure in run time. Embedded system which has high complexity is vulnerable to soft errors. In a consolidated memory bit-cell area, one bit upset that can ruin a solitary bit-cell can now corrupt the contiguous regions also. A large number of bit upsets happen when data is passed starting with one end then onto the next. To address this issue, several techniques are introduced to detect multiple errors and increase the rectification rate. To ensure against soft errors, a high level process for identification and correction of errors of has been proposed. The method is known as HVD7Q (Horizontal-Vertical-Diagonal-7-Queen-Parity). For each row, column, forward and backward diagonal and queen parity line, this approach relies on parities in all the 5 dimensions. This method works on a 7x7 cell area and can correct up to 5 bit upsets in horizontal, vertical, forward diagonal and backward diagonal. The analysis demonstrates the legitimacy of this current methodology's usefulness by contrasting out its productivity from current methodologies.

Tolerating Soft Errors with Horizontal-Vertical-Diagonal-N-Queen (HVDNQ) Parity

Published In:Journal of Electronic Testing SpringerLink(03 May 2021).

Muhammad Sheikh Sadi, Sumaiya , Mouly Dewan, Atikur Rahman

A new error detection and correction methodology, defined as Horizontal-Vertical-Diagonal-N-Queen-Parity (HVDNQ), is proposed in this paper. This approach relies on five different types of parities: horizontal parity, vertical parity, forward diagonal parity, backward diagonal parity, and queen parity. This method works on an N X N cell area and can correct multi-bit upsets. The experimental analysis validates the effectiveness of the proposed methodology by comparing its efficiency with existing methodologies. In different varieties of error patterns such as equilateral triangle, pentagon, hexagon etc., the capability of error detection and correction of HVDNQ is much better than existing methods.