An ear biometric system based on artificial bees and the scale invariant feature transform

Extraction and expression of features are critical to improving the recognition rate of ear image recognition. This paper proposes a new ear recognition method based on SIFT (Scale-invariant feature transform) and Forstner corner detection technology. Firstly, Forstner corner points and SIFT keypoints are detected respectively. Then taking Forstner corner into the SIFT algorithm to calculate their descriptor as the image feature vectors. Finally ear recognition based on these feature is carried out with Euclidean distance as similarity measurement. A bi-directional matching algorithm is utilized for improving recognition rate. Experiments on USTB database show that the recognition rate reaches more 94%. The Experimental results prove the effectiveness of the proposed method in term of recognition accuracy in comparison with previous methods. It is robust to rigid changes of ear image and provides a new approach to the research for ear recognition. DOI: http://dx.doi.org/10.11591/telkomnika.v11i12.2760

In this paper a novel method is proposed to improve the performance of the SIFT (Scale Invariant Feature Transformation) algorithm in adverse illumination conditions (in an outdoor environment at night), for this research it is proposed to work with CLAHE (Contrast Limited Adaptive Histogram Equalization), adding a preprocessing stage to the traditional methodology of the SIFT algorithm, this will be applied to the building to be found in the scene, i.e., the image pattern.A comparison with different illumination conditions (day, evening and night) will be held to know the response that will have the SIFT algorithm and to identify which moment the algorithm has a better performance.

Perspective methods of human identification: Ear biometrics

The identification of COVID-19 using chest X-ray (CXR) images plays a critical role in managing the pandemic by providing a rapid, non-invasive, and accessible diagnostic tool. This study evaluates the impact of different image preprocessing techniques on the performance of deep learning models for COVID-19 classification based on COVID-19 Radiography Database, which includes 10,192 normal CXR images, 6012 lung opacity (non-COVID lung infection) images, and 1345 viral pneumonia images. Along with the images, corresponding lung masks are also included to aid in the segmentation and analysis of lung regions. Specifically, three convolutional neural network (CNN) models were developed, each using a distinct preprocessing method: Contrast Limited Adaptive Histogram Equalization (CLAHE), traditional histogram equalization, and no preprocessing. The results revealed that while the CLAHE-enhanced model achieved the highest training accuracy (93.26%) and demonstrated superior stability during training, it showed lower performance in the validation phase, with validation accuracy of 91.31%. In contrast, the model with no preprocessing, which exhibited slightly lower training accuracy (92.98%), outperformed the CLAHE model during validation, achieving the highest validation accuracy of 91.50% and the lowest validation loss. The histogram equalization model demonstrated performance similar to that of CLAHE but with slightly higher validation loss and accuracy compared to the unprocessed model. These findings suggest that while CLAHE excels in enhancing image details during training, it may lead to overfitting and reduced generalization ability. In contrast, the model without preprocessing showed the best generalization and stability, indicating that preprocessing techniques should be chosen carefully to balance feature enhancement with the need for generalization in real-world applications. This study underscores the importance of selecting appropriate image preprocessing techniques to enhance deep learning models' performance in medical image classification, particularly for COVID-19 detection. Histogram Equalization The results contribute to ongoing efforts to optimize diagnostic tools using AI and image processing.

A contrast enhancement method for improving the segmentation of breast lesions on ultrasonography

This paper presents a comparative analysis of fundus image enhancement techniques to detect diabetic retinopathy (DR). Medical images frequently suffers from non-uniform illumination, poor contrast and noise, thus these images have to go through pre-processing stage. For image enhancement many techniques are proposed based on spatial domain (histogram). However, these methods usually decline to produce suitable consequences for non-uniform illumination and wide-ranging of low-contract. The comparative analysis and performance evaluation of various enhancement techniques will help in choosing most suitable technique which may significantly improve the detection of diabetic retinopathy. In this paper histogram equalization (HE), adaptive histogram equalization (ADHE), contrast limited adaptive histogram equalization (CLAHE) and exposure based sub-image histogram equalization (ESIHE) techniques are compared for pre-processing of fundus image for detecting DR. For fair analysis of these techniques, histogram, SNR, entropy, absolute mean brightness error and peak signal-to-noise ratio (PSNR) of fundus images are analyzed by using MATLAB.

With the advancement of technology and its implementation in the medical field, a lot of new methods and techniques are created to solve complex real-life problems. Breast cancer is a major issue in women and corresponds to a quarter of deaths related to it. In this paper, we have used the MIAS dataset which consists of 322 mammograms (161 pairs). Mammograms are cheap and easy to understand. For contrast enhancement, we have used contrast limited adaptive histogram equalization (CLAHE) with a clip size of 0.2. We have compared the PSNR of histogram equalization (HE), CLAHE, minimum mean brightness error bi-histogram equalization (MMBEBHE), and recursive mean-separate histogram equalization (RMSHE). We found that CLAHE and RMSHE perform better than MMBHBHE and HE. A convolutional neural network (CNN) architecture is created for feature extraction, and a total of 2115 features is provided for classification. SVM, decision tree, and random forest are used as classifiers. The accuracy achieved by SVM, decision tree, and random forest is 92.30, 94.03, and 95.05%, while using decision fusion (SVM, decision tree, and random forest), the highest accuracy of 96.12% is achieved.KeywordsBreast cancerCLAHEImage fusionMachine learning

Personal identification using 2D ear images still has many problems such as occlusion mostly caused by hair, earrings, and clothes. To avoid this problem, we propose to divide the ear image into non-overlapping equal divisions and identify persons through these non -occluded parts separately and then combine outputs of the classification of these parts in abstract, rank, and measurement level fusion. Experimental results show that the increasing of recognition rate through combining small parts of non -occluded divisions of ear image.

In order to improve recognition rate of human ear, a method based on point feature of image for ear recognition is proposed in this paper. Firstly force field transformation theory is applied to human ear image two times in our method. It can extract the structural feature points and contour feature points of ear respectively and compose feature point set. Then feature points described by the scale invariant feature transformation descriptor. At last nearest neighbor classifier is employed for ear recognition. Feature points extracted from ear image using force field transformation are stable, reliable and discriminative, and they are insensitive to variations in image resolution. Constructing descriptor can resolve the problems caused by lower recognition owing to illumination change, scaling transformation, rotation and minute alteration caused by pose transformation. The experimental results show that the proposed algorithm not only can effectively improve ear recognition rate but also has quite good robustness.

Ear recognition: More than a survey

Image registration is an essential step in many remote-sensing (RS) applications. This article presents a study of a multisource image automatic registration system (MIARS) based on the scale-invariant feature transform (SIFT), which has been demonstrated to be the most robust local invariant feature descriptor for automatically registering various RS images. The SIFT descriptor has two shortcomings: it is unsuitable for extremely large images and has an irregular distribution of feature points. Therefore, three steps are proposed for the MIARS: image division, histogram equalization and the elimination of false point matches by a subregion least squares iteration. Image division makes it possible to use the SIFT descriptor to extract control points from an extremely large RS image. Histogram equalization in prematching improves the contrast sensitivity of RS images. The subregion least squares iteration refines the registration accuracy. Images from multisensor systems, including Quickbird, IRS-P6, Landsat/TM, HJ-CCD, HJ-IRS, light detection and ranging (LiDAR) intensity images and aerial data, were selected to test the reliability of the MIARS. The results indicated that better registration accuracy was achieved, which will be very helpful in the future development of a registration model.

Road crack detection is a crucial safety measure for any country, especially in regions with complex road networks. In India, most roads are well-connected to cities and urban areas. However, urban roads often suffer frequent damage due to various factors. This study focuses on detecting road damage in Indian urban areas using a Deep Convolutional Neural Network (DCNN). We have developed a model specifically designed for identifying cracks in Indian urban roads. To evaluate the proposed model, we collected over 700 images of damaged roads from different urban locations across Tamil Nadu. In this work, we employed the DCNN algorithm for road crack detection, which has proven to be an efficient approach. The proposed method incorporates Histogram Equalization (HE) and Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance the contrast of road images. This is the first initiative aimed at developing a road damage detection system tailored to urban roadways in India. A comparative analysis was conducted during the preprocessing stage by applying both HE and CLAHE techniques. The model was trained using 5,000 roadside images, including both cracked and non-cracked surfaces. During training, image enhancement was performed using HE and CLAHE, and the processed images were then used to train DCNN. For testing, 700 roadside images (with and without cracks) were utilized, following the same preprocessing steps. The model's accuracy was determined based on its ability to correctly identify road cracks. Results indicate that the proposed model performs effectively for crack detection on CLAHE-enhanced images of Indian urban roads. Additionally, the proposed model's performance was compared with existing models such as ResNet, VGG16, and VGG19 using the same dataset. Evaluation metrics including accuracy, precision, recall, and F1-score were used. The proposed model achieved 98.6% accuracy, 98.5% precision, 99.6% recall, and a 99% F1-score.

Images captured in the sand–dust weather often suffer from serious colour cast and poor contrast, and this has serious implications for outdoor computer vision systems. To address these problems, a normalised gamma transformation‐based contrast‐limited adaptive histogram equalisation (CLAHE) with colour correction in Lab colour space for sand–dust image enhancement is proposed in this study. This method consists of image contrast enhancement and image colour correction. To avoid producing new colour deviation, the input sand–dust images are first transformed from red, green, and blue colour space into Lab colour space. Then, the contrast of the lightness component (L channel) of the sand–dust image is enhanced using CLAHE. To avoid unbalanced contrast, as well as to reduce the overincreased brightness caused by CLAHE, a normalised gamma correction function is introduced to CLAHE. After that, the a and b chromatic components are recovered by a grey‐world‐based colour correction method. Experiments on real sand–dust images demonstrate that the proposed method can obtain the highest percentage of new visible edges for all testing images. The contrast restoration exhibits good colour fidelity and proper brightness.

In the field of image processing, improving low-contrast images is essential for enhancing the visibility of features that may be hard to see due to slight intensity variations. This issue often arises with images captured in poor lighting or unfavorable conditions, which can impede tasks such as feature extraction, object recognition, and edge detection. This paper presents an algorithm that employs fuzzy techniques to enhance low-contrast images. The approach utilizes a Pythagorean fuzzy set, which is an advanced version of a fuzzy set. The Pythagorean fuzzy set, by integrating membership and non−membership degrees, offers a more precise representation of image uncertainty. The proposed method constructs an increasing function to calculate the degree of non−membership, thereby amplifying the effectiveness of the enhanced image. By integrating this method with contrast limited adaptive histogram equalization, alongside a color restoration technique and brightness-preserving dynamic histogram equalization, the brightness and natural appearance of the original low-contrast image are maintained. We compare our approach to other methods, including conventional histogram equalization, intuitionistic fuzzy generators, interval−valued intuitionistic fuzzy generators, interval−valued intuitionistic fuzzy with contrast limited adaptive histogram equalization, LightNet, and FlightNet. Experimental results indicate that our method surpasses the techniques currently utilized in terms of visibility and color accuracy. Performance evaluation is performed using metrics such as the absolute mean brightness error, contrast improvement index, and structural similarity index.

When only one sample per person (OSPP) is registered in the gallery, it is difficult for ear recognition methods to sufficiently and effectively reduce the search range of the matching features, thus resulting in low computational efficiency and mismatch problems. A 3D ear biometric system using OSPP is proposed to solve this problem. By categorising ear images by shape and establishing the corresponding relationship between keypoints from ear images and regions (regional cluster) on the directional proposals that can be arranged to roughly face the ear image, the corresponding keypoints are obtained. Then, ear recognition is performed by combining corresponding keypoints and a multi-keypoint descriptor sparse representation classification method. The experimental results conducted on the University of Notre Dame Collection J2 dataset yielded a rank-1 recognition rate of 98.84%; furthermore, the time for one identification operation shared by each gallery subject was 0.047 ms.