Ajay Boyat
Ajay Boyat has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Brijendra Kumar Joshi
MCTE, Mhow, India
4 shared publications Dinesh Yadav
2 shared publications- Aditya Mandloi
Electronics and Communication Dept., Medicaps University, Indore, M.P., India
1 shared publication Arpita Joshi
Department of ECE, SDBCT, Indore, India
1 shared publicationBrijendra Kumar Joshi
1 shared publicationPurshottam Singh Rathore
Engineering Department, Akashvani Indore, Indore, India
1 shared publication
Latest Publications
- Open Access
- 27 March 2026
- Published by Polish Academy of Sciences Chancellery in Management and Production Engineering Review
- Vol. 17 (1) , 1-17
Quality Assessment of Production Using Image Segmentation
Quality assessment of manufactured products is vital to ensure performance, safety, and customer satisfaction across industries. Defects in items such as bottle caps, cables, capsules, leather, and metal components can affect functionality and durability. Traditional inspection methods relying on manual visual checks are time-consuming and error-prone. This study proposes an AI driven framework using the Probabilistic U-Net integrated with a Conditional Variational Autoencoder (CVAE) for automated defect detection. The model introduces stochastic latent variables to generate multiple plausible segmentation maps, enhancing accuracy under ambiguous or noisy conditions. Using the MVTec Anomaly Detection dataset, which includes defects such as scratches and discoloration, the system applies preprocessing steps including resizing, normalization, and data augmentation to enhance the robustness and consistency of the input data. A hybrid loss combining cross-entropy and Kullback–Leibler divergence improves segmentation precision and latent space alignment. Experimental results confirm robust and reliable defect detection across diverse product categories, demonstrating the model’s potential for automated manufacturing quality assurance.
- 27 March 2026
- Published by Polish Academy of Sciences Chancellery in Management and Production Engineering Review
- Vol. 17 (1) , 1-17
Open AccessQuality Assessment of Production Using Image Segmentation
Quality assessment of manufactured products is vital to ensure performance, safety, and customer satisfaction across industries. Defects in items such as bottle caps, cables, capsules, leather, and metal components can affect functionality and durability. Traditional inspection methods relying on manual visual checks are time-consuming and error-prone. This study proposes an AI driven framework using the Probabilistic U-Net integrated with a Conditional Variational Autoencoder (CVAE) for automated defect detection. The model introduces stochastic latent variables to generate multiple plausible segmentation maps, enhancing accuracy under ambiguous or noisy conditions. Using the MVTec Anomaly Detection dataset, which includes defects such as scratches and discoloration, the system applies preprocessing steps including resizing, normalization, and data augmentation to enhance the robustness and consistency of the input data. A hybrid loss combining cross-entropy and Kullback–Leibler divergence improves segmentation precision and latent space alignment. Experimental results confirm robust and reliable defect detection across diverse product categories, demonstrating the model’s potential for automated manufacturing quality assurance.
- Open Access
- 1 July 2015
- Published by ESRSA Publications Pvt. Ltd. in International Journal of Engineering Research & Technology
- Vol. V4 (07)
Comparison Analysis of a New Color HOSVD Varies De-Noising Filtering Technique for the ‘Lena’ Image Corrupted by Pepper Salt Noise
- 1 July 2015
- Published by ESRSA Publications Pvt. Ltd. in International Journal of Engineering Research & Technology
- Vol. V4 (07)
Open AccessComparison Analysis of a New Color HOSVD Varies De-Noising Filtering Technique for the ‘Lena’ Image Corrupted by Pepper Salt Noise
- Open Access
- 1 July 2015
- Published by ESRSA Publications Pvt. Ltd. in International Journal of Engineering Research & Technology
- Vol. V4 (07)
Design of Navel Adaptive TDBLMS-based Wiener Parallel to TDBLMS Algorithm for Image Noise Cancellation
Download pdf article of Design of Navel Adaptive TDBLMS-based Wiener Parallel to TDBLMS Algorithm for Image Noise Cancellation written by Dinesh Yadav, Ajay Boyat
- 1 July 2015
- Published by ESRSA Publications Pvt. Ltd. in International Journal of Engineering Research & Technology
- Vol. V4 (07)
Open AccessDesign of Navel Adaptive TDBLMS-based Wiener Parallel to TDBLMS Algorithm for Image Noise Cancellation
Download pdf article of Design of Navel Adaptive TDBLMS-based Wiener Parallel to TDBLMS Algorithm for Image Noise Cancellation written by Dinesh Yadav, Ajay Boyat
- Top Cited PapersOpen Access
- 30 April 2015
- Published by Academy and Industry Research Collaboration Center (AIRCC) in Signal & Image Processing : An International Journal
- Vol. 6 (2) , 63-75
A Review Paper : Noise Models in Digital Image Processing
- 30 April 2015
- Published by Academy and Industry Research Collaboration Center (AIRCC) in Signal & Image Processing : An International Journal
- Vol. 6 (2) , 63-75
Top Cited PapersOpen AccessA Review Paper : Noise Models in Digital Image Processing
- 1 December 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
An efficient implementation of 2-D discrete wavelet transform for high speed DSP applications
This paper presents an efficient VLSI architecture of a high speed, low power two dimensional Discrete Wavelet Transform (2-D DWT). The proposed work minimizes the resource requirement and complexity of system. Design modules were realized using basic wavelet in HDL language and MATLAB for optimizing the speed and memory requirements. The system is modeled and implemented using Xilinx VirtexE FPGA device. The simulation results obtained through Mentor graphics simulation software. The system computing rate is up to 290 M samples/s and design uses only 34.376ns combinational path delay for 8×8 image size. In this way, the developed design provides very high-speed processing.
- 1 December 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
An efficient implementation of 2-D discrete wavelet transform for high speed DSP applications
This paper presents an efficient VLSI architecture of a high speed, low power two dimensional Discrete Wavelet Transform (2-D DWT). The proposed work minimizes the resource requirement and complexity of system. Design modules were realized using basic wavelet in HDL language and MATLAB for optimizing the speed and memory requirements. The system is modeled and implemented using Xilinx VirtexE FPGA device. The simulation results obtained through Mentor graphics simulation software. The system computing rate is up to 290 M samples/s and design uses only 34.376ns combinational path delay for 8×8 image size. In this way, the developed design provides very high-speed processing.
- 1 December 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Image denoising using wavelet transform and wiener filter based on log energy distribution over Poisson-Gaussian noise model
Generally Gaussian noise model is used in image processing applications due to its presence in electronic circuitry used in image acquisition devices like Charge Coupled Device (CCD) cameras. Off let due to discrete nature of electromagnetic radiation in image acquisition process, due to photon noise that follows poison distribution is also exist with Gaussian noise. In this paper we present an algorithm based on Wavelet transform and wiener filter using log energy distribution to denoised digital images corrupted by Poisson-Gaussian noise. Our results clearly demonstrate the robustness of the algorithm over a large range of variance. We have used peak signal to noise ratio (PSNR) for comparison based on filter outlet.
- 1 December 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Image denoising using wavelet transform and wiener filter based on log energy distribution over Poisson-Gaussian noise model
Generally Gaussian noise model is used in image processing applications due to its presence in electronic circuitry used in image acquisition devices like Charge Coupled Device (CCD) cameras. Off let due to discrete nature of electromagnetic radiation in image acquisition process, due to photon noise that follows poison distribution is also exist with Gaussian noise. In this paper we present an algorithm based on Wavelet transform and wiener filter using log energy distribution to denoised digital images corrupted by Poisson-Gaussian noise. Our results clearly demonstrate the robustness of the algorithm over a large range of variance. We have used peak signal to noise ratio (PSNR) for comparison based on filter outlet.
- 1 February 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 838-843
Impact of Wavelet Transform and Median Filtering on removal of Salt and Pepper Noise in Digital Images
Image acquisition is a common task in every image processing operation. Noise is entered (luring image acquisition from its source and once entered it degrades the image and is difficult to remove. In order to achieve the noise cancellation in an image, non-linear filter works better than linear. This paper presents the joint scheme of Wavelet Transform using iterative noise density and Median Filtering to remove Salt and Pepper Noise in Digital Images. The first part of the paper derives the wavelet coefficients with slight increase in noise density and in second part these coefficients are further modified by median filter. The algorithm shows the remarkable improvement over Gaussian noise model and removes most of the noisy part from the image and maintains the visual quality. The level of wavelet decomposition is restricted to three. The renowned indexes Peak Signal to Noise Ratio (PSNR) and Root Mean Square Error (RMSE) demonstrate marked improvement of image denoising over Gaussian method.
- 1 February 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 838-843
Impact of Wavelet Transform and Median Filtering on removal of Salt and Pepper Noise in Digital Images
Image acquisition is a common task in every image processing operation. Noise is entered (luring image acquisition from its source and once entered it degrades the image and is difficult to remove. In order to achieve the noise cancellation in an image, non-linear filter works better than linear. This paper presents the joint scheme of Wavelet Transform using iterative noise density and Median Filtering to remove Salt and Pepper Noise in Digital Images. The first part of the paper derives the wavelet coefficients with slight increase in noise density and in second part these coefficients are further modified by median filter. The algorithm shows the remarkable improvement over Gaussian noise model and removes most of the noisy part from the image and maintains the visual quality. The level of wavelet decomposition is restricted to three. The renowned indexes Peak Signal to Noise Ratio (PSNR) and Root Mean Square Error (RMSE) demonstrate marked improvement of image denoising over Gaussian method.
- 1 November 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 23751282,p. 1-6
Image denoising using wavelet transform and median filtering
During acquisition of an image, from its source, noise becomes integral part of it, which is very difficult to remove. Various algorithms have been used in past to denoise images. Image denoising still has scope for improvement. In this paper we present a new image denoising algorithm based on combined effect of wavelet transform and median filtering. The algorithm removes most of the noisy part from the image and maintains the quality. The level of wavelet decomposition is restricted to three. The renowned index Peak Signal to Noise Ratio (PSNR) and Root Mean Square Error (RMSE) demonstrate marked improvement of image denoising over other methods.
- 1 November 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 23751282,p. 1-6
Image denoising using wavelet transform and median filtering
During acquisition of an image, from its source, noise becomes integral part of it, which is very difficult to remove. Various algorithms have been used in past to denoise images. Image denoising still has scope for improvement. In this paper we present a new image denoising algorithm based on combined effect of wavelet transform and median filtering. The algorithm removes most of the noisy part from the image and maintains the quality. The level of wavelet decomposition is restricted to three. The renowned index Peak Signal to Noise Ratio (PSNR) and Root Mean Square Error (RMSE) demonstrate marked improvement of image denoising over other methods.
- 1 September 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 37, 1-4
Speech signal analysis using Fourier-Bessel Expansion and Hilbert Transform Separation Algorithm
Voiced speech is produced from time-varying vocal tract system stimulated by excitation source. The analysis of speech signal is important for various applications like speech synthesis, bandwidth compression encoding and transmission purposes. Non-stationary nature of excitation source and vocal tract system makes analysis of speech signal a difficult task. In this paper non parametric method is proposed to analyze the speech signal using Fourier-Bessel expansion (FB) to separate multiple formants of speech signal in one step and not requiring prior information about frequency band of the resonance signals. The Hilbert Transform Separation Algorithm (HTSA) is applied to an isolated speech formant to extract the instantaneous frequency (IF) and the time varying amplitude envelope (AE) of the formant. The HTSA provides the best available time resolution of the amplitude and other estimations of signal analysis. For any other digital method the spectral resolution is a discrete and terminal value that can not be less than the ratio between the sampling frequency and the number of measured points. In contrast, the HTSA calculates the frequency as the rate of phase change with time, and the instantaneous frequency resolution can be as small as desired depending on the accuracy of the signal phase and time measurement. It also opens the way for averaging and for other statistical processing procedures, making signal analysis more precise. The proposed method is simple and fast, thus allowing online (real-time) signal analysis and identification.
- 1 September 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 37, 1-4
Speech signal analysis using Fourier-Bessel Expansion and Hilbert Transform Separation Algorithm
Voiced speech is produced from time-varying vocal tract system stimulated by excitation source. The analysis of speech signal is important for various applications like speech synthesis, bandwidth compression encoding and transmission purposes. Non-stationary nature of excitation source and vocal tract system makes analysis of speech signal a difficult task. In this paper non parametric method is proposed to analyze the speech signal using Fourier-Bessel expansion (FB) to separate multiple formants of speech signal in one step and not requiring prior information about frequency band of the resonance signals. The Hilbert Transform Separation Algorithm (HTSA) is applied to an isolated speech formant to extract the instantaneous frequency (IF) and the time varying amplitude envelope (AE) of the formant. The HTSA provides the best available time resolution of the amplitude and other estimations of signal analysis. For any other digital method the spectral resolution is a discrete and terminal value that can not be less than the ratio between the sampling frequency and the number of measured points. In contrast, the HTSA calculates the frequency as the rate of phase change with time, and the instantaneous frequency resolution can be as small as desired depending on the accuracy of the signal phase and time measurement. It also opens the way for averaging and for other statistical processing procedures, making signal analysis more precise. The proposed method is simple and fast, thus allowing online (real-time) signal analysis and identification.