Department of Electrical and Electronics Engineering

Permanent URI for this collectionhttp://localhost:4000/handle/123456789/1925

Browse

Author: search.filters.author.Bhatt, Upendra MohanSubject: search.filters.subject.EEE

Search Results

Now showing 1 - 10 of 26
  • No Thumbnail Available
    Item
    DWT based image super resolution performance analysis
    (IJRET, 2016-12) Bhatt, Upendra Mohan
    In computer vision field, Image resolution enhancement has become the most current research area. Improving image resolution by applying costly hardware is expensive and time-consuming. Many algorithms have been developed by researchers based on Projection Onto Convex Set (POCS), Maximum-aposteriori (MAP) and Maximum Likelihood (ML) In this paper, we analyzed a super resolution algorithm based on Discrete Wavelet Transform (DWT). Single frame super resolution can be achieved by use of different interpolation method but this scheme generates blur at the edges of images. Hence in this paper we relied on wavelet transform for super resolution algorithm with different orthogonal and bi-orthogonal filters. Quality aspect of images such as MSE, PSNR, SSIM and Correlation Coefficient (CC) are calculated with this proposed algorithm.
  • No Thumbnail Available
    Item
    DWT and sparse representation based image super resolution
    (2016) Bhatt, Upendra Mohan
    Spatial resolution of images are restricted by the size of CMOS sensors. Spatial resolution can be increased by increasing no of COMS sensors resulting in decrease in size of CMOS sensors which cause shot noise. In this paper attempts have been made to enhance the spatial resolution of different images. DWT is applied to obtain the sub bands and sparse representation is used to get the better results. Bicubic interpolation is being applied in the intermediary stage and HR image is retrieved through this method and the result of this method is being compared with some other state of the art works and this work shows better result than other super resolution algorithms based on image quality parameter PSNR and MSE
  • No Thumbnail Available
    Item
    A Review on Image Resolution Enhancement Methods in Spatial and Frequency Domain
    (IJCSMC, 2016-06) Bhatt, Upendra Mohan
    Zooming a picture is ver essential in the field where someone wants to obtain more detailed information from an image. Low resolution(LR) images do not contain more information so to retrieve more information from that image Super-resolution(SR) is applied on LR images. The resolution enhancement work began in 1984 when Tsai and Huang [1] has introduced a mathematical model to obtain a single high-resolution image from a single or multiple LR images. This paper provides the review of the work done in the area of super-resolution in the spatial as well as in the frequency domain. This paper is organized into following sections. Section II describes spatial domain methods of super-resolution, section III gives method in the frequency domain, section IV contains comparison between some of the well-known algorithms and finally in the last section Conclusion is drawn.
  • No Thumbnail Available
    Item
    Performance analysis of wavelet filter bank for an image super resolution algorithm
    (IEEE, 2017-07) Bhatt, Upendra Mohan
    Image super-resolution is a technique in which a high-resolution image is generated using a single or multiple low-resolution images. In this paper, an image super-resolution algorithm is proposed in which Discrete wavelet transform (DWT) is used to generate different frequency sub-bands of the image and Stationary wavelet transform (SWT) overcomes the issue of lack of translation invariance of DWT so it is used here with DWT. To preserve more edge information Canny Edge extraction operator has been applied to the input image and subbands are interpolated using Lanczos interpolation. The high-frequency sub bands and the input image are passed through Non-Local Mean (NLM) filter to reduce the artifacts generated by DWT. Different orthogonal and bi-orthogonal filters have been applied to this algorithm and different quality parameters such as PSNR, MSE, RMSE, SSIM and Correlation coefficient are calculated. It is found that db2 wavelet is showing better results.
  • No Thumbnail Available
    Item
    Image super resolution based on discrete and Stationary wavelet transform using Canny edge extraction and non local mean
    (IEEE, 2017-01) Bhatt, Upendra Mohan
    This paper addresses the issue of generating a high-resolution(HR) image from single low quality or low-resolution(LR) image. In this work, Discrete wavelet transform (DWT) is used with the Stationary wavelet transform (SWT) to generate or increase the resolution of the image. SWT reduces the translation invariance presence in DWT. To preserve the edges Canny edge extraction is used to get the sharper image. To interpolate the image into the intermediary stage of proposed algorithm Lanczos interpolation is used and to reduce the artifacts introduced by the DWT Non-local mean(NLM) filter has been used. The experimental result shows that the proposed algorithm gives good results based on image quality parameters as compared with the state-of-the-art works in super resolution (SR) process.
  • No Thumbnail Available
    Item
    Detection of suspicious lesions in mammogram using fuzzy C-means algorithm
    (IEEE, 2016-11) Bhatt, Upendra Mohan
    Breast cancer is one of the most incurable diseases, which leads to the death of women globally every year. For initial detection of a tumor in the breast, the most useful technique called `Mammography' is used, which is an X-ray inspection of the breast, which can be used to detect the breast tumor which may lead to breast cancer. Using Mammography, a small lump that may lead to breast cancer can be detected at the initial stage. Sometimes it is not possible to recognize very small tumors because of noisy, blurred, and fuzzy images. Therefore, they need to be enhanced to increase the contrast for better visual perception and reduce the noise from it for better diagnosis. In this work, FCM algorithm is used to detect the suspicious lesions in a mammogram. To achieve the objective of this work, MIAS (Mammographic Image Analysis Society) and INbreast databases are used, which contain 322 and 412 images of the breast (both left and right breast) respectively. In these databases, every image is examined by the expert radiologists. The effectiveness of the algorithm is measured in terms of MSE and PSNR.
  • No Thumbnail Available
    Item
    Leaf classification and identification using Canny Edge Detector and SVM classifier
    (IEEE, 2017-10) Bhatt, Upendra Mohan
    Plants are to be considered as one of the important things that plays a very essential role for all living beings exists on earth. But due to some unawareness and environment deterioration, some very rare plants are on the verge of extinction. Knowledge of rare leaves used for medicine and other plants is very critical in future. Leaf identification and classification plays a vital role for plant species recognition. In recent years, most of the researchers dedicate their work on leaf characterization. Leaf shape is the major parameter to classify plants. A new approach is to extract 15 features from the leaf using Canny Edge Detector and classify 22 different kinds of plants with SVM classifier.
  • No Thumbnail Available
    Item
    Comparision between sizes of original HR images and images obtained through super resolution
    (IEEE, 2018-02) Bhatt, Upendra Mohan
    Getting high detailed information through LR(low resolution) images is not possible, so research in the field of computer science leads toward converting the LR images to the HR(high resolution) images and this process is known as Super resolution. In this paper a super resolution algorithm is proposed which uses DWT and SWT to downsampled the images and to preserve the edges Canny edge extractor and to remove the noise NLM filter is added to the algorithm. This paper shows the comparision between the sizes of original HR images on which experiment is done and the images obtained after converting LR image to HR with this algorithm. Result shows that the HR image obtained after the experiment is so much lesser in size than original HR image
  • No Thumbnail Available
    Item
    Performance Enhancement by Optimization of Poly Grain Size and Channel Thickness in a Vertical Channel 3-D NAND Flash Memory
    (IEEE, 2018) Bhatt, Upendra Mohan
    String read current (Iread) reduction with rising mold height and grain boundary traps is one of the major hurdle in the development of 3-D NAND flash memory. In this paper, we have investigated Iread with variation in polysilicon channel grain size (GS), grain boundary trap density, and channel thickness (TSi), using TCAD. We find that under a critical value of GS, Iread decreases with increase in TSi. This is attributed to the fact that with smaller GS, the total number of grain boundaries and associated traps are significantly higher. Moreover, there exists a typical value of GS for which Iread is independent of TSi, which is desirable to minimize the deviations in Iread arising from TSi variations. The resulting tradeoff in the design of more efficient 3-D NAND flash is demonstrated and discussed. Further, it is found that Iread increases significantly by limiting the polysilicon channel grain boundary trap concentration under 1012 cm-2. The results presented in this paper are crucial for optimizing Iread and program/erase threshold voltage(VT) window, and serve as key guidelines in the design of 3-D NAND flash memory with better performance.
  • No Thumbnail Available
    Item
    Effect of String Tapering on Threshold Voltage Distribution and Its Mitigation in a Vertical Channel 3D NAND Flash Memory
    (ICSDM, 2018) Bhatt, Upendra Mohan
    In this work, we have investigated the impacts of taper angle and channel doping on the performance parameters of a vertical channel 3D NAND flash memory. It is found that string current and threshold voltage (VT) distribution of the word lines (WLs) along the string is influenced by both, taper angle and channel doping. Therefore, nonuniformity in VT distribution of different WLs due to string tapering is minimized by optimizing the channel doping along the string from top to bottom. Moreover, optimized channel doping leads to an improved string current. These results are crucial for the designing of high performance and reliable future 3D NAND flash memories.