scholarly journals COMPUTER AIDED ANALYSIS OF LUNG CT BASED ON TRANSFORM DOMAIN FEATURES

2014 ◽  
pp. 244-249
Author(s):  
V. MINNAL
Keyword(s):  
Wavelet Transforms ◽  
Spatial Domain ◽  
Classification Performance ◽  
Transform Domain ◽  
Pixel Intensity ◽  
Second Stage ◽  
Contour Segmentation ◽  
Spatial Features ◽  
Computer Aided Analysis ◽  
Combined Feature

As Many CADx systems have been developed to detect lung cancer based on spatial domain features that process only the pixel intensity values, the proposed scheme applies frequency transform to the lung images to extract frequency domain features and they are combined with spatial features so that the features that are not revealed in spatial domain will be extracted and the classification performance can be tuned up. The proposed CADx comprises of four stages. In the first stage, lung region is segmented using Convexity based active contour segmentation. At second stage ROIs are extracted using spatially constrained KFCM clustering. Followed by standard wavelet transforms is applied on ROI so that transform domain features are extracted with shape and haralick histogram features. Finally neural network is trained by combined feature set to identify the cancerous nodules. Our proposed scheme has shown sensitivity of 95% and specificity of 96%.

Moving Object Classification in a Video Sequence

2017 ◽  
pp. 70-101
Author(s):  
S. Vasavi ◽  
T. Naga Jyothi ◽  
V. Srinivasa Rao
Keyword(s):  
Wavelet Transforms ◽  
Moving Objects ◽  
Performance Test ◽  
Texture Features ◽  
Classification Performance ◽  
Object Identification ◽  
Svm Classifier ◽  
Classification Methods ◽  
Military Installations ◽  
Outdoor Environments

Now-a-day's monitoring objects in a video is a major issue in areas such as airports, banks, military installations. Object identification and recognition are the two important tasks in such areas. These require scanning the entire video which is a time consuming process and hence requires a Robust method to detect and classify the objects. Outdoor environments are more challenging because of occlusion and large distance between camera and moving objects. Existing classification methods have proven to have set of limitations under different conditions. In the proposed system, video is divided into frames and Color features using RGB, HSV histograms, Structure features using HoG, DHoG, Harris, Prewitt, LoG operators and Texture features using LBP, Fourier and Wavelet transforms are extracted. Additionally BoV is used for improving the classification performance. Test results proved that SVM classifier works better compared to Bagging, Boosting, J48 classifiers and works well in outdoor environments.

scholarly journals Fractal Image Interpolation: A Tutorial and New Result

2019 ◽  
Vol 3 (1) ◽  
pp. 7
Author(s):  
Chi Kok ◽  
Wing Tam
Keyword(s):  
Image Interpolation ◽  
Spatial Domain ◽  
Fractal Interpolation ◽  
Image System ◽  
Pixel Intensity ◽  
Resolution Image ◽  
Fractal Image ◽  
Pros And Cons ◽  
Simulation Results ◽  
Visual Artifacts

This paper reviews the implementation of fractal based image interpolation, the associated visual artifacts of the interpolated images, and various techniques, including novel contributions, that alleviate these awkward visual artifacts to achieve visually pleasant interpolated image. The fractal interpolation methods considered in this paper are based on the plain Iterative Function System (IFS) in spatial domain without additional transformation, where we believe that the benefits of additional transformation can be added onto the presented study without complication. Simulation results are presented to demonstrate the discussed techniques, together with the pros and cons of each techniques. Finally, a novel spatial domain interleave layer has been proposed to add to the IFS image system for improving the performance of the system from image zooming to interpolation with the preservation of the pixel intensity from the original low resolution image.

scholarly journals Optimal Feature Subset Selection for Imbalanced Class Data using SMOTE and Binary ALO Algorithm

2020 ◽  
Vol 9 (3) ◽  
pp. 344-349
Keyword(s):  
Feature Selection ◽  
Class Imbalance ◽  
Classification Performance ◽  
Selection Model ◽  
Feature Subset Selection ◽  
Feature Subset ◽  
Spatial Features ◽  
Imbalanced Classes ◽  
Optimal Feature Subset ◽  
Optimal Feature

Feature selection in multispectral high dimensional information is a hard labour machine learning problem because of the imbalanced classes present in the data. The existing Most of the feature selection schemes in the literature ignore the problem of class imbalance by choosing the features from the classes having more instances and avoiding significant features of the classes having less instances. In this paper, SMOTE concept is exploited to produce the required samples form minority classes. Feature selection model is formulated with the objective of reducing number of features with improved classification performance. This model is based on dimensionality reduction by opt for a subset of relevant spectral, textural and spatial features while eliminating the redundant features for the purpose of improved classification performance. Binary ALO is engaged to solve the feature selection model for optimal selection of features. The proposed ALO-SVM with wrapper concept is applied to each potential solution obtained during optimization step. The working of this methodology is tested on LANDSAT multispectral image.

scholarly journals Advanced Multifocus Image Fusion algorithm using FPDCT with Modified PCA

2019 ◽  
Vol 9 (2) ◽  
pp. 175-184
Keyword(s):  
Image Fusion ◽  
Wavelet Transforms ◽  
Quality Evaluation ◽  
State Of The Art ◽  
Principal Component ◽  
Fusion Algorithm ◽  
Pixel Intensity ◽  
Wide Range ◽  
Value Decomposition ◽  
Processing Techniques

Image fusion has been performed and reported in this paper for multi-focused images using Frequency Partition Discrete Cosine Transform (FP-DCT) with Modified Principal component analysis (MPCA) technique. The image fusion with decomposition at fixed levels may be treated as a very critical rule in the earlier image processing techniques. The frequency partitioning approach was used in this study to select the decomposition levels based on the pixel intensity and clarity. This paper also presents the modified PCA technique which provides dimensionality reduction. The wide range of quality evaluation metrics was computed to compare the fusion performance on the five images. Different techniques such as PCA, wavelet transforms with PCA, Multiresolution Singular Value Decomposition (MSVD) with PCA, Multiresolution DCT (MRDCT) with PCA, Frequency partitioning DCT (FP-DCT) with PCA were computed for comparison with the proposed FP-DCT Modified PCA (MPCA) technique. Images obtained after fusion process obtained by the method proposed shows enhanced visual quality, negligible information loss and discontinuities in the image than compared to other state of the art methods.

scholarly journals A 3D-2D Multibranch Feature Fusion and Dense Attention Network for Hyperspectral Image Classification

Micromachines ◽  
2021 ◽  
Vol 12 (10) ◽  
pp. 1271
Author(s):  
Hongmin Gao ◽  
Yiyan Zhang ◽  
Yunfei Zhang ◽  
Zhonghao Chen ◽  
Chenming Li ◽  
...  
Keyword(s):  
Image Classification ◽  
Hyperspectral Image ◽  
Feature Fusion ◽  
Receptive Fields ◽  
Classification Performance ◽  
Redundant Information ◽  
Hyperspectral Image Classification ◽  
Training Process ◽  
Attention Network ◽  
Spatial Features

In recent years, hyperspectral image classification (HSI) has attracted considerable attention. Various methods based on convolution neural networks have achieved outstanding classification results. However, most of them exited the defects of underutilization of spectral-spatial features, redundant information, and convergence difficulty. To address these problems, a novel 3D-2D multibranch feature fusion and dense attention network are proposed for HSI classification. Specifically, the 3D multibranch feature fusion module integrates multiple receptive fields in spatial and spectral dimensions to obtain shallow features. Then, a 2D densely connected attention module consists of densely connected layers and spatial-channel attention block. The former is used to alleviate the gradient vanishing and enhance the feature reuse during the training process. The latter emphasizes meaningful features and suppresses the interfering information along the two principal dimensions: channel and spatial axes. The experimental results on four benchmark hyperspectral images datasets demonstrate that the model can effectively improve the classification performance with great robustness.

scholarly journals Sparse Approach in Filtering of Color Images Corrupted by Mixture Noises

2020 ◽  
Vol 16 ◽  
Keyword(s):  
Noise Suppression ◽  
Impulsive Noise ◽  
Median Filter ◽  
Color Images ◽  
Subjective Perception ◽  
Transform Domain ◽  
Second Stage ◽  
Novel Approach ◽  
Impulsive Noises ◽  
Impulsive Noise Suppression

A novel filtering approach is presented in denoising in the color images contaminated by mixture of additive-impulsive noises. Novel framework consists of three principal stages: impulsive noise suppression that is performed detecting pixels corrupted by impulsive noise and then, filtering found spikes by a variant of median filter; during second stage, original additive noise suppression filter is employed in Wavelet transform domain via a sparse representation and 3D-filtering; finally, nondesirable effects obtained in an image during previous stages are processed to correct fine details. In case of multiplicative noise suppression, the designed denoising scheme uses 3D homomorphic sparse processing stage and post-filtering procedure. Evaluation of novel approach in denoising complex distortions has been performed using objective criteria (PSNR and SSIM measures) and subjective perception via human visual system confirming their better performance in comparison with state-of-theart techniques.

Target Object Recognition Using Multiresolution SVD and Guided Filter with Convolutional Neural Network

2020 ◽  
Vol 34 (12) ◽  
pp. 2052008
Author(s):  
Biswajit Biswas ◽  
Swarup Kr Ghosh ◽  
Anupam Ghosh ◽  
Chandan Chakraborty ◽  
Pabitra Mitra
Keyword(s):  
Weighted Average ◽  
Target Object ◽  
Guided Filter ◽  
Pixel Intensity ◽  
Spatial Features ◽  
Segmentation Methods ◽  
Fused Image ◽  
Convolutional Autoencoder ◽  
Value Decomposition ◽  
Fusion Scheme

To design an efficient fusion scheme for the generation of a highly informative fused image by combining multiple images is still a challenging task in computer vision. A fast and effective image fusion scheme based on multi-resolution singular value decomposition (MR-SVD) with guided filter (GF) has been introduced in this paper. The proposed scheme decomposes an image of two-scale by MR-SVD into a lower approximate layer and a detailed layer containing the lower and higher variations of pixel intensity. It generates lower and details of left focused (LF) and right focused (RF) layers by applying the MR-SVD on each series of multi-focus images. GF is utilized to create a refined and smooth-textured weight fusion map by the weighted average approach on spatial features of the lower and detail layers of each image. A fused image of LF and RF has been achieved by the inverse MR-SVD. Finally, a deep convolutional autoencoder (CAE) has been applied to segment the fused results by generating the trained-patches mechanism. Comparing the results by state-of-the-art fusion and segmentation methods, we have illustrated that the proposed schemes provide superior fused and its segment results in terms of both qualitatively and quantitatively.

scholarly journals Two-Layer Fragile Watermarking Method Secured with Chaotic Map for Authentication of Digital Holy Quran

2014 ◽  
Vol 2014 ◽  
pp. 1-29 ◽  
Author(s):  
Mohammed S. Khalil ◽  
Fajri Kurniawan ◽  
Muhammad Khurram Khan ◽  
Yasser M. Alginahi
Keyword(s):  
Wavelet Transforms ◽  
Wavelet Coefficient ◽  
Chaotic Map ◽  
Spatial Domain ◽  
Fragile Watermarking ◽  
Discrete Wavelet ◽  
Discrete Wavelet Transforms ◽  
Wavelet Domain ◽  
Good Image Quality ◽  
Holy Quran

This paper presents a novel watermarking method to facilitate the authentication and detection of the image forgery on the Quran images. Two layers of embedding scheme on wavelet and spatial domain are introduced to enhance the sensitivity of fragile watermarking and defend the attacks. Discrete wavelet transforms are applied to decompose the host image into wavelet prior to embedding the watermark in the wavelet domain. The watermarked wavelet coefficient is inverted back to spatial domain then the least significant bits is utilized to hide another watermark. A chaotic map is utilized to blur the watermark to make it secure against the local attack. The proposed method allows high watermark payloads, while preserving good image quality. Experiment results confirm that the proposed methods are fragile and have superior tampering detection even though the tampered area is very small.

Medical Image Fusion in Spatial and Transform Domain

2017 ◽  
pp. 281-300
Author(s):  
Alka Srivastava ◽  
Ashwani Kumar Aggarwal
Keyword(s):  
Wavelet Transform ◽  
Image Fusion ◽  
Medical Image ◽  
Medical Images ◽  
Spatial Domain ◽  
Transform Domain ◽  
Fusion Technique ◽  
Medical Image Fusion ◽  
Domain Fusion ◽  
Fused Image

Nowadays, there are a lot of medical images and their numbers are increasing day by day. These medical images are stored in the large database. To minimize the redundancy and optimize the storage capacity of images, medical image fusion is used. The main aim of medical image fusion is to combine complementary information from multiple imaging modalities (e.g. CT, MRI, PET, etc.) of the same scene. After performing medical image fusion, the resultant image is more informative and suitable for patient diagnosis. There are some fusion techniques which are described in this chapter to obtain fused image. This chapter presents two approaches to image fusion, namely spatial domain Fusion technique and transforms domain Fusion technique. This chapter describes Techniques such as Principal Component Analysis which is spatial domain technique and Discrete Wavelet Transform and Stationary Wavelet Transform which are Transform domain techniques. Performance metrics are implemented to evaluate the performance of image fusion algorithm.

scholarly journals Fully Dense Multiscale Fusion Network for Hyperspectral Image Classification

2019 ◽  
Vol 11 (22) ◽  
pp. 2718 ◽  
Author(s):  
Zhe Meng ◽  
Lingling Li ◽  
Licheng Jiao ◽  
Zhixi Feng ◽  
Xu Tang ◽  
...  
Keyword(s):  
Hyperspectral Image ◽  
Multiple Scales ◽  
Feature Learning ◽  
Classification Performance ◽  
Connectivity Pattern ◽  
Great Success ◽  
Feature Representations ◽  
Spatial Features ◽  
Discriminative Feature ◽  
Correlated Information

The convolutional neural network (CNN) can automatically extract hierarchical feature representations from raw data and has recently achieved great success in the classification of hyperspectral images (HSIs). However, most CNN based methods used in HSI classification neglect adequately utilizing the strong complementary yet correlated information from each convolutional layer and only employ the last convolutional layer features for classification. In this paper, we propose a novel fully dense multiscale fusion network (FDMFN) that takes full advantage of the hierarchical features from all the convolutional layers for HSI classification. In the proposed network, shortcut connections are introduced between any two layers in a feed-forward manner, enabling features learned by each layer to be accessed by all subsequent layers. This fully dense connectivity pattern achieves comprehensive feature reuse and enforces discriminative feature learning. In addition, various spectral-spatial features with multiple scales from all convolutional layers are fused to extract more discriminative features for HSI classification. Experimental results on three widely used hyperspectral scenes demonstrate that the proposed FDMFN can achieve better classification performance in comparison with several state-of-the-art approaches.

Sign in / Sign up

Export Citation Format

Share Document