Gabor Feature Extraction Research Articles

Lip2Speech: Lightweight Multi-Speaker Speech Reconstruction with Gabor Features

In environments characterised by noise or the absence of audio signals, visual cues, notably facial and lip movements, serve as valuable substitutes for missing or corrupted speech signals. In these scenarios, speech reconstruction can potentially generate speech from visual data. Recent advancements in this domain have predominantly relied on end-to-end deep learning models, like Convolutional Neural Networks (CNN) or Generative Adversarial Networks (GAN). However, these models are encumbered by their intricate and opaque architectures, coupled with their lack of speaker independence. Consequently, achieving multi-speaker speech reconstruction without supplementary information is challenging. This research introduces an innovative Gabor-based speech reconstruction system tailored for lightweight and efficient multi-speaker speech restoration. Using our Gabor feature extraction technique, we propose two novel models: GaborCNN2Speech and GaborFea2Speech. These models employ a rapid Gabor feature extraction method to derive lowdimensional mouth region features, encompassing filtered Gabor mouth images and low-dimensional Gabor features as visual inputs. An encoded spectrogram serves as the audio target, and a Long Short-Term Memory (LSTM)-based model is harnessed to generate coherent speech output. Through comprehensive experiments conducted on the GRID corpus, our proposed Gabor-based models have showcased superior performance in sentence and vocabulary reconstruction when compared to traditional end-to-end CNN models. These models stand out for their lightweight design and rapid processing capabilities. Notably, the GaborFea2Speech model presented in this study achieves robust multi-speaker speech reconstruction without necessitating supplementary information, thereby marking a significant milestone in the field of speech reconstruction.

Expression Recognition Based on Gabor Filter

We propose a comprehensive approach that integrates traditional methods with deep learning techniques to address the challenges of insufficient feature extraction, limited feature discriminability, and dimensionality catastrophe in facial expression recognition. This method begins by artificially extracting image features using Gabor filters to effectively capture relevant information within the images. Subsequently, Principal Component Analysis (PCA) is employed to reduce feature dimensions, controlling feature space while eliminating redundant information introduced by Gabor feature extraction, resulting in a novel feature representation. The reduced-dimensional features are fed into a Convolutional Neural Network (CNN), where multi-layered convolution and pooling operations extract abstract features and enable classification training. Experimental results demonstrate that the proposed method achieves impressive performance on the CK+ dataset, with an accuracy of 98.98%, signifying a substantial improvement over traditional approaches.

Traditional technique application v/s YOLOv5 model for marine underwater objects detection by computer vision method

The paper compares the effectiveness of two methods application for detecting and recognizing micro-objects in an aqua environment on the example of plankton using neural networks and various technologies and developed in different programming languages. At first the traditional detection method was investigated and applied based on the extraction of Gabor and multilayer perceptron features, realized in MATrixLABoratory (MATLAB) language. Secondly, YOLOv5 (an acronym for ‘You only look once’), as a single-stage neural network was used which was implemented in Python language. The results of the work of these methods for the plankton detection are presented. Accuracy and completeness metrics are calculated to determine best of two methods. Images with the recognition result, programmatically calculated performance metrics were obtained after using the detection methods. The study was conducted on the effectiveness of method applications for realtime recognition using short video images. In conclusion it is stated that the YOLOv5 model has shown significant superiority over the traditional method in the task of detecting marine objects, in particular plankton. Its accuracy was 30% higher; the completeness of object detection was 27% higher.

An efficient approach for detecting brain tumors using a modified artificial neural network

ABSTRACT Computed Tomography (CT) was a prominent technique for detecting brain tumours. Tradition models have some drawbacks, such as that they do not predict the accurate position of the tumour, are time-consuming, involve complex operations, and have low accuracy. In order to solve these issues, Modified Artificial Neural Network (ANN) was proposed to detect brain tumour in a CT image. Initially the raw images were pre-processed to improve contrast and reduce the noise using contrast stretching and median filtering. Then the features were extracted from the pre-data by using gradient filter, Local Binary Pattern, Gabor feature extraction, and Histogram of oriented gradients. The extracted features were given to the modified ANN model to predict the disease. The prediction performance of the classifier was improved by selecting the appropriate weight of the ANN. The optimal selection of weight was done through the use of sailfish optimisation algorithm. The proposed method obtained 94% accuracy, while existing systems such as SVM, KNN, RF, and NB reached 90%, 85%, 74% and 72% accuracy, respectively, which is lower than the proposed method. The proposed early and accurate diagnosis of brain tumour model thus effectively detects the tumour and provides necessary treatment based on this diagnosis.

Maize Plant Leaf Disease Classification Using Supervised Machine Learning Algorithms

Maize is an important staple crop all over the world, and its health is very important for food security. It is important for crop management and yield to find diseases that affect maize plants as soon as possible. In this study, we suggest a new way to classify diseases on maize plant leaves by using supervised machine learning algorithms. Our method uses the power of texture analysis with Gray-Level Co-occurrence Matrix (GLCM) and Gabor feature extraction techniques on the Plant-Village dataset, which has images of both healthy and unhealthy maize leaves. This method uses four supervised machine learning algorithms, called Decision Tree, Gradient Boosting, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN), to sort the extracted features into healthy and diseased groups. By doing a lot of tests, we show that our way of finding maize leaf diseases works well. The results show that these techniques have the potential to quickly and non-invasively diagnose diseases, giving farmers important information for acting quickly. We talk about the pros and cons of each algorithm and suggest ways to make them even better. This research contributes to the advancement of automated plant disease detection systems, fostering sustainable agriculture practices and aiding in crop management decisions. The proposed approach holds promise for real-world application, enabling farmers to mitigate disease-related losses and secure global food supplies.

A Framework for Verification in Contactless Secure Physical Access Control and Authentication Systems

Biometrics is one of the very popular techniques in user identification for accessing institutions and logging into attendance systems. Currently, some of the existing biometric techniques such as the use of fingerprints are unpopular due to COVID-19 challenges. This paper identifies the components of a framework for secure contactless access authentication. The researcher selected 50 journals from Google scholar which were used to analyze the various components used in a secure contactless access authentication framework. The methodology used for research was based on the scientific approach of research methodology that mainly includes data collection from the 50 selected journals, analysis of the data and assessment of results. The following components were identified: database, sensor camera, feature extraction methods, matching and decision algorithm. Out of the considered journals the most used is CASIA database at 40%, CCD Sensor camera with 56%, Gabor feature extraction method at 44%, Hamming distance for matching at 100% and PCA at 100% was used for decision making. These findings will assist the researcher in providing a guide on the best suitable components. Various researchers have proposed an improvement in the current security systems due to integrity and security problems.

DETECTION OF LUNG CANCER USING IMAGE PROCESSING

This project constructs and assesses an image processing approach for lung cancer diagnosis in this study. Image processing techniques are frequently utilized for picture improvement in the detection phase to enable early medical therapy in a variety of medical issues. We suggested a lung cancer detection approach based on picture segmentation in this study. Image segmentation is a level of image processing that is intermediate. To segment a CT scan image, a marker control watershed and region growth technique is applied. Following the detection phases, picture augmentation with the Gabor filter, image segmentation, and feature extraction is performed. We discovered the efficiency of our strategy based on the experimental results. The results demonstrate that the watershed with the masking method, which has great accuracy and robustness, is the best strategy for detecting major features. Keywords: Lung cancer, MATLAB, CT images, Distortion removal, Segmentation, Mortality rate.

Application of Gabor Image Recognition Technology in Intelligent Clothing Design

Aiming at the complex problem of image recognition feature extraction, this paper proposes an intelligent clothing design model based on parallel Gabor image feature extraction algorithm. Based on the intelligent parallel mode, the algorithm decomposes and merges the calculation process of the image Gabor transformation, decomposes the entire image Gabor feature extraction calculation process into a parallel part and a nonparallel part, and accelerates the parallel part by using multiple cores. The calculation results are then combined to achieve the purpose of multicore parallel acceleration of the entire calculation process. Secondly, based on the consideration of improving the real-time performance of the intelligent clothing design system, combined with the existing multicore environment, this paper uses the intelligent model to design and implement the image parallel Gabor feature extraction algorithm and uses image processing and analysis technology to analyze the visual elements of traditional clothing and identify and quantify to form a relatively complete clothing visual element evaluation system, which provides a basis for large-scale collection and automated evaluation of clothing visual effects, as well as clothing trend tracking and prediction. Experiments show that the algorithm can effectively shorten the calculation time of Gabor image feature extraction and can obtain a good speedup in a multicore environment. At the same time, it combines with a multiscale intelligent clothing classification algorithm, on the basis of the VS2008 platform, combined with OpenCV 2.0, designed and implemented an intelligent clothing design system, and conducted experiments and system tests. The experimental results show that the algorithm given in this paper can accurately segment fabric defects from the background, which proves that the detection algorithm has a good detection effect. Simulation results show that the algorithm proposed in this paper can more accurately identify the state of clothing features, and the real-time performance of intelligent clothing design in a multicore environment has been improved to a certain extent.

Gabor Features Extraction and Land-Cover Classification of Urban Hyperspectral Images for Remote Sensing Applications

The principles of the transform stage of the extract, transform and load (ETL) process can be applied to index the data in functional structures for the decision-making inherent in an urban remote sensing application. This work proposes a method that can be utilised as an organisation stage by reducing the data dimension with Gabor texture features extracted from grey-scale representations of the Hue, Saturation and Value (HSV) colour space and the Normalised Difference Vegetation Index (NDVI). Additionally, the texture features are reduced using the Linear Discriminant Analysis (LDA) method. Afterwards, an Artificial Neural Network (ANN) is employed to classify the data and build a tick data matrix indexed by the belonging class of the observations, which could be retrieved for further analysis according to the class selected to explore. The proposed method is compared in terms of classification rates, reduction efficiency and training time against the utilisation of other grey-scale representations and classifiers. This method compresses up to 87% of the original features and achieves similar classification results to non-reduced features but at a higher training time.

Recognizing Face Image Based on Gabor and DCT Feature Extraction using SVM

Recognizing Face Image Based on Gabor and DCT Feature Extraction using SVM

Phase-Induced Gabor-Based Multiview Active Learning for Hyperspectral Image Classification

In this letter, we propose a new phase-induced Gabor-based multiview active learning (MVAL) (PGMVAL) approach for hyperspectral image (HSI) classification. Our main contribution is to explore the potential of the phase offset term <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$P$ </tex-math></inline-formula> in hand-crafted Gabor feature extraction, which is rarely exploited in previous works. The Gabor filters with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$P$ </tex-math></inline-formula> added, named as the phase-induced Gabor filters, are able to adjust their frequency response characteristics through <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$P$ </tex-math></inline-formula> . Specifically, we utilize the phase-induced Gabor filtering for view generation purposes under a MVAL framework. As a result, PGMVAL is capable to exploit the complementary information residing in the phase-induced Gabor features corresponding to different <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$P\text{s}$ </tex-math></inline-formula> and simultaneously avoids high memory consumption and a large number of training samples required caused by introducing a new parameter. The experimental results obtained on two benchmark HSI data sets show that the proposed PGMVAL approach using phase-induced Gabor filtering could achieve better classification results with limited training samples.

Face Recognition Based on Gabor Feature Extraction Followed by FastICA and LDA

Face Recognition Based on Gabor Feature Extraction Followed by FastICA and LDA

A Cloud Detection Method Using Convolutional Neural Network Based on Gabor Transform and Attention Mechanism with Dark Channel Subnet for Remote Sensing Image

Cloud detection, as a crucial step, has always been a hot topic in the field of optical remote sensing image processing. In this paper, we propose a deep learning cloud detection Network that is based on the Gabor transform and Attention modules with Dark channel subnet (NGAD). This network is based on the encoder-decoder framework. The information on texture is an important feature that is often used in traditional cloud detection methods. The NGAD enhances the attention of the network towards important texture features in the remote sensing images through the proposed Gabor feature extraction module. The channel attention module that is based on the larger scale features and spatial attention module that is based on the dark channel subnet have been introduced in NGAD. The channel attention module highlights the important information in a feature map from the channel dimensions, weakens the useless information, and helps the network to filter this information. A dark channel subnet with spatial attention module has been designed in order to further reduce the influence of the redundant information in the extracted features. By introducing a “dark channel”, the information in the feature map is reconstructed from the spatial dimension. The NGAD is validated while using the Gaofen-1 WFV imagery in four spectral bands. The experimental results show that the overall accuracy of NGAD reaches 97.42% and the false alarm rate reaches 2.22%. The efficiency of cloud detection using NGAD exceeds the state-of-art image segmentation network model and remote sensing image cloud detection model.

Exploiting Gabor Feature Extraction Method for Chinese Character Writing Quality Evaluation

The automatic evaluation of Chinese character writing quality has a wide application prospect. Most of the existing evaluation methods of Chinese character writing quality are based on radical segmentation and feature judgment, which require the high accuracy of Chinese character segmentation. However, there are many problems in the real handwriting, such as continuous writing, uneven strength of writing, personalized writing style and so on, which lead to the difficulty of segmentation in the ordinary handwriting. To solve the above problems, we propose an effective method based on image texture where the uniformity of writing lines and writing style is taken as an effective criterion. In our method, Gabor transform is used to extract the image features of writing samples, and finally the statistical learning method of support vector machine is used to effectively evaluate the writing quality. Experiments on multiple real datasets including CHAED show that our method is effective and accurate. The advantage of this method is that it does not need to segment fonts, and the cost of global feature extraction is small.

The Implementation of Deep Learning Using Convolutional Neural Network to Classify Based on Stomata Microscopic Image of Curcuma Herbal Plants

There are so many types of herbal plants that come from the same genus. The similarity of features in herbal plants makes it difficult to distinguish. Especially in the pharmaceutical field, which is very risky for making mistakes. The part of plants that is often used as ingredients for herbal medicines is the leaves, so research on leaves and their constituent organelles is very important for the pharmaceutical world. Therefore, an approach is needed to identify the types of organelles present in the leaves, where the organelles most frequently studied are the stomata. So, a neural network approach is needed to distinguish plant characteristics in the same genus. In this research there are 2 species of plants in the Curcuma genus, namely turmeric and ginger. This research was conducted by implementing Deep Learning using Convolutional Neural Network (CNN) with the help of the Gabor filter process and feature extraction using the Gray Level Co-occurrence Matrix (GLCM). The study was conducted using 160 microscopic images of Curcuma herbal plants as training data with training accuracy of 93.1% and test data of 40 images with an accuracy of 92.5%.

The Optimized Classification of Mammograms Based on the Antlion Technique

Breast cancer is one of the main health issues for women. This disease can be cured only if detected at early stages. Digital mammography is used to detect the malignant cells at an early stage. This article designs a methodology to detect the malignant tumors. The methodology is comprised of preprocessing feature extraction by Gabor and Law's feature extraction, and feature reduction by ant-lion optimization as well as a classification step using a SVM classifier which is implemented on the live dataset prepared through the Rajindra Hospital Patiala along with MIAS and DDSM datasets. The results of proposed techniques have been compared with three states of art techniques SVM based classification without feature reduction, PSOWNN i.e. PSO based reduction with a neural network as a classifier and binary gray wolf-based feature reduction with SVM classifier. The performance analysis proves the significance of the technique.

Light Field Image Quality Assessment via the Light Field Coherence

In this paper, a novel full-reference image quality assessment (IQA) method for evaluating the quality of the distorted light field (LF) image against its reference LF image is proposed, called the log-Gabor feature-based light field coherence (LGF-LFC). Based on the fact that to compare two LF images, it essentially boils down to measure how coherent of these two LF images, we attempt to measure the degree of their LF coherence (LFC). To pursue this goal, the salient features from the reference and distorted LF images under comparison need to be extracted. By considering that the Gabor feature has the ability to well characterize the human visual system (HVS) perception, and the special characteristics of the LF images, the multi -scale and single -scale Gabor feature extraction schemes are developed to extract the multi-scale log-Gabor features from the sub-aperture images (SAIs) and the single-scale log-Gabor feature from the epi-polar images (EPIs), respectively. Note that the former can reflect the image details (via the SAIs), while the latter indicates the viewing consistency (via the EPI’s depth information). The similarity measurements are subsequently conducted on the comparison of their SAIs and that of their EPIs separately, followed by combining them together for arriving at the final score. Extensive simulation results have clearly demonstrated that the proposed LGF-LFC is more consistent with the perception of the HVS on the quality evaluation of the LF images than multiple classical and state-of-the-art IQA methods.

Gabor Feature Based LogDemons with Inertial Constraint for Nonrigid Image Registration.

Nonrigid image registration plays an important role in the field of computer vision and medical application. The methods based on Demons algorithm for image registration usually use intensity difference as similarity criteria. However, intensity based methods can not preserve image texture details well and are limited by local minima. In order to solve these problems, we propose a Gabor feature based LogDemons registration method in this paper, called GFDemons. We extract Gabor features of the registered images to construct feature similarity metric since Gabor filters are suitable to extract image texture information. Furthermore, because of the weak gradients in some image regions, the update fields are too small to transform the moving image to the fixed image correctly. In order to compensate this deficiency, we propose an inertial constraint strategy based on GFDemons, named IGFDemons, using the previous update fields to provide guided information for the current update field. The inertial constraint strategy can further improve the performance of the proposed method in terms of accuracy and convergence. We conduct experiments on three different types of images and the results demonstrate that the proposed methods achieve better performance than some popular methods.

Segmentation of retinal blood vessels based on feature-oriented dictionary learning and sparse coding using ensemble classification approach.

Accurate segmentation of the blood vessels from a retinal image plays a significant role in the prudent examination of the vessels. A supervised blood vessel segmentation technique to extract blood vessels from a retinal image is proposed. The uniqueness of the work lies in the implementation of feature-oriented dictionary learning and sparse coding for the accurate classification of the pixels in an image. First, the image is split into patches and for each patch, Gabor features are extracted at multiple scales and orientations to create a set of feature vectors (this is done for the whole training set). Then, an overcomplete feature-oriented dictionary is trained from the extracted Gabor features (selected on the basis of standard deviation) using the generalized K-means for singular value decomposition dictionary learning technique. Sparse representations are subsequently calculated for the corresponding features from the dictionary. The combination of feature vectors and sparse representations constitutes the final feature vector. This feature vector is then fed into the ensemble classifier for the classification of pixels into either blood vessel pixels or nonblood vessel pixels. The method is evaluated on publicly available DRIVE and STARE datasets, as they contain ground truth images precisely marked by experts. The results obtained on both of the datasets show that the proposed technique outperforms most of the state-of-the-art techniques reported in the literature.

3-D Gaussian–Gabor Feature Extraction and Selection for Hyperspectral Imagery Classification

Hyperspectral remote sensing imagery provides valuable and rich information to distinguish the characteristics of materials. However, this advantage of hyperspectral imagery often encounters the problem of a limited amount of training samples, which is caused by the difficulty of manually labeling. Fortunately, the spatial distribution of surface objects can be integrated with the spectral signature to improve the discriminative ability. In this paper, a 3-D Gaussian–Gabor feature extraction and selection framework has been proposed for hyperspectral image classification. First, a bank of 3-D Gaussian–Gabor filters are convolved with the concatenated data of both extended multi-attribute profile (EMAP) features and raw hyperspectral data. Second, an improved fast density peak clustering (IFDPC) method is introduced to select the most representative features from each extracted 3-D Gaussian–Gabor feature cube. Finally, the retained features are combined together to accomplish the classification task. The proposed method is thus named as GG-IFDPC. Three real hyperspectral imagery data sets have been utilized, and the experiments demonstrate the advantages of the proposed GG-IFDPC approach over the compared ones.