Analysis of image compression methods based on wavelet transforms for maritime applications

The purpose of the article is to develop recommendations for choosing image compression method based on wavelet transformation, depending on image type, quality and compression requirements. Among the wavelet image compression methods, Embedded Zerotree Wavelet coder (EZW) and Set Partition In Hierarchical Trees (SPIHT) are considered, and the Haar wavelet and wavelet transformation in the oriented basis with the first, third, fifth and seventh decomposition levels is used as the base wavelet transform. These compression methods were compared with each other and with the standard JPEG method on the following parameters: mean square error, maximum error, peak to noise ratio, number of bits per pixel, compression ratio, and image size. The proposed methods can be successfully applied in the transmission of seabed relief images obtained from satellites or sea buoys.

A Critical Analysis of the Multi-Focus Images Fusion Based on Discrete Wavelet Transform and Computer Vision

This paper focused on the challenge of image fusion processing and lack of reliable image information and proposed multi-focus image fusion using discrete wavelet transforms and computer vision techniques for the fused image coefficient selection process. I made an in-depth analysis and improvement on the existing algorithms from the wavelet transform and the rules of multi-focus image fusion object features’ extractions. The wavelet transform uses authentic localization properties, and computer vision provides efficient processing time and is a powerful method to analyze object focus in the high-frequency precision and steps. The process of image fusion using wavelet transformation is the wavelet basis function and wavelet decomposition level in iterative experiments to enhance fused image information. The rules of multi-focus image fusions are the wavelet transformation on the features of the high-frequency coefficients, which enhance the fusion image features reliability on the frequency domain and regional contrast of the object.

Advanced Watermarking o f Digital Images Showing Robust, Semi Fragile a nd Fragile Behaviour

Digital Image Watermarking plays an important role when it comes to maintaining digital color picture authentication information. The proposed paper consists mainly of a digital watermarking scheme consisting of discrete wavelet transformation and involving the generation of pn sequence number to embed the watermark and also to extract the watermark from the host image. The technique suggested includes both embedding the watermark and removing it from the host file. Both the method of embedding and extraction consists of generating the pn sequence number values using the random numbers. The technique for all three of the RGB signal sources is included. The watermark symbol is located independently within the RGB image's red, green, and blue channels. The suggested technique further reveals the improved mode of digital watermarking of images through fragile watermarking of images and semi-fragile digital watermarking of images.

Devanagari Handwritten Marathi Compound Character Recognition System

Handwritten character recognition a field of research in AI, computer vision, and pattern recognition. Devanagari handwritten Marathi compound character recognition is most tedious tasks because of its complexity as compared to other languages. As compound character is combination of two or more characters it becomes challenging task to recognize it. However, the researchers used various methods like Neural Network, SVM, KNN, Wavelet transformation to classify the features of compound Marathi characters and tried to give the accuracy in the recognition of it. But the problem of feature extraction, and time required is large. In this paper I am proposing the Offline handwritten Marathi compound character recognition using deep convolution neural network which reduces the computational time and increases the accuracy.

Acoustic emission as a valuable technique used for monitoring polymer failures

In the paper, acoustic emission (AE) system was presented as a method that can be used to monitor polymer material failures. Samples fabricated of two aluminum profiles bonded together with a thick layer of cured epoxy resin were subjected to fracture tests. Epidian 53 epoxy resin cured with Z1 curing agent as well as Epidian 5 epoxy resin cured with PAC curing agent were selected as adhesives. Acoustic emission parameters were acquired during Double Cantilever Beam (DCB) tests. The frequencies of elastic waves released during failure were then analyzed using both Fast Fourier Transformation (FFT) and Wavelet Transformation (WT) for the two materials.

Harumanis Mango Leaves Image Segmentation based on Wavelet Transformation with Phansalkar and Sauvola Thresholding

Harumanis mango is one of the economic sources of the Perlis state. It has a sweeter taste compared to other mangoes. However, the Harumanis mango tree required specific weather, soil nutrient contents and pH level. This makes the farmer does not know the health condition of their Harumanis mango tree. Therefore, this project aims to provide the best method of leaves detection to the farmer. The leaves image samples are collecting from the orchard and undergo pre-processing. Then the input image was converted into grayscale with principal component analysis (PCA). Wavelet transformation was implemented to increase the discriminability of the segmentation technique for separating the leaf and background. The leaf segmentation is done by using Phansalkar and Sauvola thresholding techniques. After that, fill hole and area opening techniques are implementing to reduce noise in the image. These two thresholding techniques are comparing and discuss with their segmentation performance. Overall, Phansalkar thresholding has produced better performance in segmenting healthy and unhealthy Harumanis mango leaves with sensitivity, specificity and accuracy of 92.05%, 81.37% and 83.51%, respectively.

Proposal of noninvasive failure diagnosis of electrical motor using googlenet

Fault diagnosis is a useful tool that reduces system maintenance risks and costs. However, data related to the system's nominal and fault operating behavior is often not collected and stored adequately, it is difficult to identify and suggest automated fault detection methods. This study proposes a solution to apply deep learning technique on the convolutional neural network (CNN) to identify some common errors on induction motors based on operation sound. The opreration sound signal emitted from on a 0.37 kW two-pole induction motor is collected in some cases such as normal operation, phase loss, phase difference and bearing breakage. Their 2-D scalogram images are analyzed by continuous Wavelet transformation which is used to train and evaluate the deep learning CNN (i.e. GoogLeNet) to identify the above faults. Experimental results show that this method can diagnose induction motor faults with accuracy up to 98.8%.