Application of Convolutional Neural Network for Image Classification on Pascal VOC Challenge 2012 dataset

Shetty, Suyash

doi:10.48550/arxiv.1607.03785

Cited by 10 publications

(14 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the early stage, FCN [31] introduced fully convolutional architectures to generate a spatial segmentation map for a given image of any size. After that, deconvolution operation was introduced by Noh et al [34] and achieved impressive performance on PASCAL VOC 2012 dataset [39]. Inspired by FCN, U-Net [37] is proposed for especially the medical image segmentation domain, which bridges the information flow between corresponding low-level and high-level feature maps with the same spatial sizes.…”

Section: Dense Prediction Tasksmentioning

confidence: 99%

Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions

Wang

Xie

et al. 2021

Preprint

216

472

View full text Add to dashboard Cite

Section: Dense Prediction Tasksmentioning

confidence: 99%

Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions

Wang

Xie

et al. 2021

Preprint

216

472

View full text Add to dashboard Cite

“…In this paper, the images in PASCAL 2012 [25] were selected as the experimental data set, including Figure 3a-f (numbered 000019, 000436, 001478, 003579, 004423, 006404). They were typical images with relatively centralized gray distribution and small inter class variance, while Figure 3g-l (numbered 001236, 001876, 002036, 004231, 004610, 006946) selected images with obvious differences in gray distribution, that is, the inter class variance was relatively large, as shown in Figure 3.…”

Section: Segmentation Experiments and Resultsmentioning

confidence: 99%

“…Experiments demonstrate the effectiveness of our improved multi-threshold image segmentation algorithm. The test image is taken from the PASCAL 2012 data set [25]. The experimental environment consists of MATLAB 2018a, Windows 10, and an Intel(R) Core(TM) i5-5600H @ 2.4GHz CPU with 8GB of RAM.…”

Section: Experimental Environmentmentioning

confidence: 99%

OTSU Multi-Threshold Image Segmentation Based on Improved Particle Swarm Algorithm

et al. 2022

View full text Add to dashboard Cite

In view of the slow convergence speed of traditional particle swarm optimization algorithms, which makes it easy to fall into local optimum, this paper proposes an OTSU multi-threshold image segmentation based on an improved particle swarm optimization algorithm. After the particle swarm completes the iterative update speed and position, the method of calculating particle contribution degree is used to obtain the approximate position and direction, which reduces the scope of particle search. At the same time, the asynchronous monotone increasing social learning factor and the asynchronous monotone decreasing individual learning factor are used to balance global and local search. Finally, chaos optimization is introduced to increase the diversity of the population to achieve OTSU multi-threshold image segmentation based on improved particle swarm optimization (IPSO). Twelve benchmark functions are selected to test the performance of the algorithm and are compared with the traditional meta-heuristic algorithm. The results show the robustness and superiority of the algorithm. The standard dataset images are used for multi-threshold image segmentation experiments, and some traditional meta-heuristic algorithms are selected to compare the calculation efficiency, peak signal to noise ratio (PSNR), structural similarity (SSIM), feature similarity (FSIM), and fitness value (FITNESS). The results show that the running time of this paper is 30% faster than other algorithms in general, and the accuracy is also better than other algorithms. Experiments show that the proposed algorithm can achieve higher segmentation accuracy and efficiency.

show abstract

“…The overall process is extremely time-consuming and costly, and the diagnosis result is fault-prone as it depends on the subjective bias of the dermatologist [6]. To address the limitations of human inspection, deep learning-based classification system utilizing big data has been proposed, e.g., ImageNet [7], MSCOCO [8], and PASCAL [9], which demonstrate high performance in terms of the detection and diagnosis of skin lesions [10][11][12][13].…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we focused on the basic components of images through relatively simple and easy feature analysis instead of using multiple detectors or performing large-scale models and complex processing as in previous studies [7][8][9][10][11][12][13][14][15][16][17]. These components are essential features used in the diagnosis of skin lesions, and we aimed to extract them to reduce the scale and complexity of neural models.…”

Section: Introductionmentioning

confidence: 99%

Skin Lesion Classification Using Hybrid Convolutional Neural Network with Edge, Color, and Texture Information

et al. 2023

View full text Add to dashboard Cite

Herein, a new paradigm based on deep learning was proposed that allows the extraction of fine-grained differences between skin lesions in pixel units for high accuracy classification of skin lesions. As basic feature information for a dermoscopic image of a skin region, 50 different features were extracted based on the edge, color, and texture features of the skin lesion image. For the edge features, a line-segment-type analysis algorithm was used, wherein the visual information of a dermoscopic image was precisely analyzed in terms of the units of pixels and was transformed into a structured pattern. Regarding the color features of skin lesions, the dermoscopic image was transformed into multiple color models, and the features were acquired by analyzing histograms showing information regarding the distribution of pixel intensities. Subsequently, texture features were extracted by applying the well-known Law’s texture energy measure algorithm. Feature data (50 × 256) generated via the feature extraction process above were used to classify skin lesions via a one-dimensional (1D) convolution layer-based classification model. Because the architecture of the designed model comprises parallel 1D convolution layers, fine-grained features of the dermoscopic image can be identified using different parameters. To evaluate the performance of the proposed method, datasets from the 2017 and 2018 International Skin Imaging Collaboration were used. A comparison of results yielded by well-known classification models and other models reported in the literature show the superiority of the proposed model. Additionally, the proposed method achieves an accuracy exceeding 88%.

show abstract

Application of Convolutional Neural Network for Image Classification on Pascal VOC Challenge 2012 dataset

Cited by 10 publications

References 0 publications

Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions

Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions

OTSU Multi-Threshold Image Segmentation Based on Improved Particle Swarm Algorithm

Skin Lesion Classification Using Hybrid Convolutional Neural Network with Edge, Color, and Texture Information

Contact Info

Product

Resources

About