Optimized lung tumor diagnosis system using enhanced version of crow search algorithm, Zernike moments, and support vector machine

Early detection of lung tumors is so important to heal this disease in the initial steps. Automatic computer-aided detection of this disease is a good method for reducing human mistakes and improving detection precision. The major concept here is to propose the best CAD system for lung tumor detection. In the presented technique, after pre-processing and segmentation of the lung area, its features including different orders of Zernike moments have been extracted. After features extraction, they have been injected into an optimized version of Support Vector Machine (SVM) for final diagnosis. The optimization of the SVM is based on an enhanced design of the Crow Search Algorithm (ECSA). For validating the proposed method, it was applied to three datasets including Lung CT-Diagnosis, TCIA, and RIDER Lung CT collection, and the results are validated by comparing with three state-of-the-art methods including Walwalker method, Mon method, and Naik method to indicate the system superiority toward the compared methods. The system is also analyzed based on different orders of Zernike moment to select the best order. The final results indicate that the suggested method has a suitable accuracy for diagnosing lung cancer.

Research on Artificial Intelligence Machine Learning Character Recognition Algorithm Based on Feature Fusion

With the continuous progress of science and information technology, people begin to study in the field of intelligence, and machine learning is one of the key contents. At present, human beings have made some progress in intelligent robot, speech recognition and network search. The method of character recognition based on machine learning is of great significance to information technology. In this paper, an improved CRNN algorithm based on feature fusion is proposed, which combines Gabor features and Zernike moment features into a new feature vector, and then uses generalized K-L transform to compress the new feature dimension to remove redundant information. After testing, the accuracy of CRNN based on feature fusion on training data set and test data set is as high as 0.99, which shows that the neural network model can perfectly fit the training set of Chinese character recognition.

Zernike Moment Based Classification of Cosmic Ray Candidate Hits from CMOS Sensors

Reliable tools for artefact rejection and signal classification are a must for cosmic ray detection experiments based on CMOS technology. In this paper, we analyse the fitness of several feature-based statistical classifiers for the classification of particle candidate hits in four categories: spots, tracks, worms and artefacts. We use Zernike moments of the image function as feature carriers and propose a preprocessing and denoising scheme to make the feature extraction more efficient. As opposed to convolution neural network classifiers, the feature-based classifiers allow for establishing a connection between features and geometrical properties of candidate hits. Apart from basic classifiers we also consider their ensemble extensions and find these extensions generally better performing than basic versions, with an average recognition accuracy of 88%.

Robust Zero Watermarking Algorithm for Medical Images Based on Zernike-DCT

Digital medical system not only facilitates the storage and transmission of medical information but also brings information security problems. Aiming at the security of medical images, a robust zero watermarking algorithm for medical images based on Zernike-DCT is proposed. The algorithm first uses a chaotic logic sequence to preprocess and encrypt the watermark, then performs edge detection and Zernike moment processing on the original medical image to get the accurate edge points, and then performs discrete cosine transform (DCT) on them to get the feature vector. Finally, it combines perceptual Hash and zero watermark technology to generate the key to complete the watermark embedding and extraction. The algorithm has good robustness to conventional and geometric attacks, strong antinoise ability, high positioning accuracy, and processing efficiency and is superior to the classical edge detection algorithm in extraction effect. It is a stable and reliable image edge detection algorithm.

Bayesian Pixel Density Estimation Modeling to Detect Human Sperm Sample Image Based on Sperm Head Shape

Currently, there is a problem of the difficulty in classifying human sperm head sample images using different databases and measuring the accuracy of several different datasets. This study proposes a Bayesian Density Estimation-based model for detecting human sperm heads with four classification labels, namely, normal, tapered, pyriform, and small or amorphous. This model was applied to three kinds of datasets to detect the level of pixel density in images containing normal human sperm head samples. Experimental results and computational accuracy are also presented. As a method, this study labeled each human sperm head based on three shape descriptors using the formulas of Hu moment, Zernike moment, and Fourier descriptor. Each descriptor was also tested in the experiment. There was an increased accuracy that reached 90% after the model was applied to the three datasets. The Bayesian Density Estimation model could classify images containing human sperm head samples. The correct classification level was obtained when the human sperm head was detected by combining Bayesian + Hu moment with an accuracy rate of up to 90% which could detect normal human sperm heads. It is concluded that the proposed model can detect and classify images containing human sperm head objects. This model can increase accuracy, so it is very appropriate to be applied in the medical field

Robust Affine Invariant Shape Descriptors

With the increasing number of available digital images, there is an urgent need of image content description to facilitate content based image retrieval (CBIR). Besides colour and texture, shape is an important low level feature in describing image content. An object can be photographed from different distances and angles. However, we often want to classify the images of the same object into one class, despite the change of perspective. So, it is desired to extract shape features that are invariant to the change of perspective. The shape of an object from one viewpoint to another can be linked through an affine transformation, if it is viewed from a much larger distance than its size along the line of sight. Those invariant shape features are known as affine invariant shape representations. Because of the change of perspective, it is more difficult to develop affine invariant shape representations than normal ones. The goal of this work is to develop affine invariant shape descriptors. Through shape retrieval experiments, we find that the performance of the existing affine invariant shape representations are not satisfactory. Especially, when the shape boundary is corrupted by noise, their performance degrades quickly. In this work, two new affine invariant contour-based shape descriptors, the ICA Fourier shape descriptor (ICAFSD) and the whitening Fourier shape descriptor (WFSD) have been developed. They perform better than most of the existing affine invariant shape representations, while having compact feature size and low computational time requirement. Four region-based affine-invariant shape descriptors, the ICA Zernike moment shape descriptor (ICAZMSD), the whitening Zernike moment shape descriptor (WZMSD), the ICA orthogonal Fourier Mellin moment shape descriptor (ICAOFMMSD), and the whitening orthogonal Fourier Mellin moment shape descriptor (WOFMMSD), are also proposed, in this work. They can be applied to both simple and complex shapes, and have close to perfect performance in retrieval experiments. The advantage of those newly proposed shape descriptors is even more apparent in experiments on shapes with added boundary noise: Their performance does not deteriorate as much as the existing ones.

Robust Affine Invariant Shape Descriptors

With the increasing number of available digital images, there is an urgent need of image content description to facilitate content based image retrieval (CBIR). Besides colour and texture, shape is an important low level feature in describing image content. An object can be photographed from different distances and angles. However, we often want to classify the images of the same object into one class, despite the change of perspective. So, it is desired to extract shape features that are invariant to the change of perspective. The shape of an object from one viewpoint to another can be linked through an affine transformation, if it is viewed from a much larger distance than its size along the line of sight. Those invariant shape features are known as affine invariant shape representations. Because of the change of perspective, it is more difficult to develop affine invariant shape representations than normal ones. The goal of this work is to develop affine invariant shape descriptors. Through shape retrieval experiments, we find that the performance of the existing affine invariant shape representations are not satisfactory. Especially, when the shape boundary is corrupted by noise, their performance degrades quickly. In this work, two new affine invariant contour-based shape descriptors, the ICA Fourier shape descriptor (ICAFSD) and the whitening Fourier shape descriptor (WFSD) have been developed. They perform better than most of the existing affine invariant shape representations, while having compact feature size and low computational time requirement. Four region-based affine-invariant shape descriptors, the ICA Zernike moment shape descriptor (ICAZMSD), the whitening Zernike moment shape descriptor (WZMSD), the ICA orthogonal Fourier Mellin moment shape descriptor (ICAOFMMSD), and the whitening orthogonal Fourier Mellin moment shape descriptor (WOFMMSD), are also proposed, in this work. They can be applied to both simple and complex shapes, and have close to perfect performance in retrieval experiments. The advantage of those newly proposed shape descriptors is even more apparent in experiments on shapes with added boundary noise: Their performance does not deteriorate as much as the existing ones.

3D Human Activity Classification with 3D Zernike Moment Based Convolutional, LSTM-Deep Neural Networks

In this paper, we propose a method for classification 3D human activities using the complementarity of CNNs, LSTMs, and DNNs by combining them into one unified architecture called CLDNN. Our approach is based on the prediction of 3D Zernike Moments of some relevant joints of the human body through Kinect using the Kinect Activity Recognition Dataset. KARD includes 18 activities and each activity consists of real-world point clouds that have been carried out 3 times by 10 different subjects. We introduce the potential for the 3D Zernike Moment feature extraction approach via a 3D point cloud for human activity classification, and the ability to be trained and generalized independently from datasets using the Deep Learning methods. The experimental results obtained on datasets with the proposed system has correctly classified 96.1% of the activities. CLDNN has been shown to provide a 5% relative improvement over LSTM, the strongest of the three individual models.

Rough Set Neural Network Feature Extraction and Pattern Recognition of Shaft Orbits Based on the Zernike Moment

In the shaft axis monitoring of hydrogenerating unit condition monitoring and fault diagnosis, the shaft orbit is intuitive and comprehensively reflects the unit operation state, and different shaft orbits correspond to different fault types, which can accurately indicate a system vibration fault. Shaft orbit identification has important significance for vibration fault diagnosis. In getting the feature extraction and pattern recognition of a shaft orbit, the Zernike moment is better than the Hu moment; it has the advantages of a small calculation error and a high recognition rate. A rough set neural network (RS-BP hybrid model) of shaft orbit recognition is established, which uses just 13 moment eigenvalues reserved by the rough set feature selection algorithm as input variables; it has the same calculation error and recognition rate and reduces the calculation time step. The simulation of the recognition of shaft orbits shows that the hybrid model has achieved good results in the identification of shaft orbits.