Retinal Identification Based on Rotation Invariant Moments

Optic Disc (OD) localization is an important step in retinal image analysis especially for grading Diabetic retinopathy and Glaucoma. This paper describes a method to automatically localize the OD position in retinal fundus images. The method localizes the OD by combining intensity and vascular information. Initially, the vascular structure is extracted using 2 dimensional Gabor filtering followed by a simple thresholding technique. Then the initial OD candidates are selected using intensity information. The candidates’ satisfying area and density criterion are considered for the final stage. In the final stage, the entropy of vascular directions on the final candidates was calculated, and the candidate having maximum and optimum entropy was considered as OD region. The proposed method was evaluated on the two publicly available DRIVE and STARE databases. The method was able to obtain 100% of OD localization accuracy on DRIVE database with 2.2 seconds average computation time.

Vessel segmentation is very important in an automatic screening system for fundus images. Vessels are often segmented and removed from retinal images before the other residual lesions are detected. Incomplete vessel removal usually causes a false positive in lesion detection, especially for Microaneurysms detection. Segmenting vessels in spatial image domain makes miss detection due to non illumination and noises in retinal images. Non-illumination problem can be disregarded by segmenting the vessels in spatial-frequency domain, which invariant subbands can be ignored. This paper presents a new retinal blood vessel segmentation method based on fractal dimension in spatial-frequency domain of retinal images. The fractal dimension value of each pixel is computed in order to extract the vessels from their retinal background. The performance of the proposed method is evaluated and compared with the experts' diagnosis in the STARE database.

We present invariant image watermarking based on a recently introduced set of polar harmonic transforms and angular radial transforms and their comparative analysis with state-of-art approaches based on Zernike moments and pseudo-Zernike moments (ZMs/PZMs). Similar to ZMs/PZMs, these transforms provide rotation invariance and resilience to noise while mitigating inherent limitations like numerical instability and computational cost at high order of moments. These characteristics motivate us to design invariant transform-based invariant image watermarking schemes that can withstand various intentional or unintentional attacks, handle large bitcarriers, and work in a limited computing environment. A comparative performance evaluation of watermarking systems regarding critical parameters like visual imperceptibility, embedding capacity, and watermark robustness against geometric transformations, common signal processing distortions, and Stirmark attacks is performed along with the empirical analysis of various inherent properties of transforms and moments such as magnitude invariance, reconstruction capabilities, and computational complexity to investigate relationships between the performance of watermarking schemes and inherent properties of transforms.

Most of the state-of-the-art Arabic Optical Character Recognition systems use Hidden Markov Models to model Arabic characters. Much of the attention is paid to provide the HMM system with new features, pre-processing, or post-processing modules to improve the performances. In this paper, we present an Arabic OCR system using Restricted Boltzmann Machines (RBMs) to model Arabic characters. The recently announced ALTEC dataset for typewritten OCR system is used to train and test the system. The results show a 26% increase in the average word accuracy rate and 8% increase in the average character accuracy rate compared to the HMM system.

The structure of the optic disc is impacted by the devastating eye disease glaucoma. Most doctors rely on viewing and screening the retinal fundus images to detect it. Identifying the optic disc is a crucial stage for automated diagnosis of glaucoma. This study presents a transfer learning-based approach to locate the optic disc in the retinal fundus image. The fundus images are categorized into four distinct classes according to the positions of optic disc to learn the in-depth specific features.Based on the YOLOv3 model, the optic disc detection method is then fine-tuned using the specialised image dataset. The model involved is trained and evaluated on 2178 retinal fundus images obtained from database at a nearby hospital and publically accessible datasets. In 2103 of the retinal fundus images, the suggested approach successfully detected the optical disc, yielding an average accuracy of 96.56%.

Fundus images are consistently used for the analysis of numerous pathological syndromes. This paper presents a three step thresholding based method to extract the blood vessels from the retinal images. In the first step a unique combination of principal component analysis (PCA) and contrast limited adaptive histogram equalization (CLAHE) is used to enhance the retinal images. In the second step the blood vessels are extracted with the help of global Otsu thresholding method. Finally in the last step morphological cleaning is applied to remove unwanted frills. The proposed method enables implementation to be easier and takes less computational time. The two publicly available DRIVE and STARE databases are taken for evaluation of the performance of the presented method. It achieves an average accuracy, sensitivity and specificity about 0.956, 0.723 and 0.984 for DRIVE database while 0.954, 0.737 and 0.982 for STARE database respectively.

Eliminating tissue-fold artifacts in histopathological whole-slide images for improved image-based prediction of cancer grade

In this paper, a simple biometric scheme based on RGB retinal fundus images is proposed. First, prominent vasculature energy based feature vectors are constructed from RGB retinal fundus images to utilize the unique pattern of retinal vasculature. Next, fast normalized cross-correlation based feature matching is employed for person identification on publicly available DRIVE and STARE databases. This method excels recently published literatures with perfect recognition accuracy of 100% on STARE and accuracy of 99.77% on DRIVE databases. Its smaller dimension of feature vector and better recognition result make this method eligible for real-time person identification scheme.

Aiming at the problem that modulated signals' classification and recognition accuracy is not high in the complex and changeable electromagnetic environment, this paper improves the CNN‐LSTM network and proposes a modulation recognition method of the CNN‐LSTM network (Intra‐InterNet) based on the periodic characteristics of the signal. The method uses the feature extraction ability of the convolutional neural network to extract the correlation features within the cycle and between adjacent cycles of different kinds of modulated signals. At the same time, the relevant features of the signals of non‐adjacent cycles are extracted by using the characteristics of the LSTM. This feature extraction method effectively enhances the feature extraction capability of the network by utilizing the periodicity of the modulated signal. Through the identification and verification of various modulation signals, the experimental results show that: under the signal‐to‐noise ratio of −6 dB ∼ 6 dB, the average identification accuracy rate reaches 87.29%, which effectively improves the accuracy of signal modulation mode identification.

In this paper, we have developed a new method of accurate detection of retinal blood vessels based on a deep convolutional neural network (CNN) model. This method plays an important role in the observation of many eye diseases. Retinal Images have many issues that make the process of vessels segmentation very hard. We treat each issue of the retina image with the greatest observation to obtain a well-segmented image. The first step is to apply a pre-processing method based on fuzzy logic and image processing tactics. In a second step, in order to generate the segmented images, we propose a strided encoder-decoder CNN model. This network is trained and optimized using the Dice Loss function that supports the class imbalance problem that is in the database. The proposed model has a U-Net shape, but it is deeper and the pooling layers are replaced with strided convolutional layers in the encoder. This modification allows for a more precise segmentation of vessels and accelerates the training process. The last step is post-processing for removing the noisy pixels as well as the shadow of the optic disc. The performance of the proposed method was evaluated on DRIVE and STARE databases. The proposed method gives a sensitivity of 0.802 and 0.801 respectively on DRIVE and STARE, with an accuracy of 0.959 and 0.961 respectively. We focused on sensitivity and accuracy measurements that represent the accuracy of the model, especially tiny vessels. According to the results, the model outperforms many other proposed methods, especially in the above-mentioned measures.

Retinal vessel segmentation takes a significant part in an automated diabetic retinopathy screening task. However, this can be a challenging job because of the low contrast retinal images and the presences of retinal pathologies. Hence, in this paper, we propose a novel matched filter based on the modified Chebyshev type I function for retinal blood vessels candidates detection. The proposed method is combined with the pre-processing and the post-processing phases to have a complete retinal vessel segmentation scheme. The retinal images from the DRIVE and STARE databases, which are equipped with the ground truths are used to evaluate our proposed method in the segmentation scheme. Using our method, the achieved average levels of sensitivity, specificity, and accuracy are 0.756, 0.973, and 0.954, for the DRIVE database, and 0.731, 0.972, and 0.953, for the STARE database, being better than other presented methods. The high results indicate that our method is reliable to be used in an automated detection tool for diabetic retinopathy.

The low-contrast and narrow blood vessels in retinal images are difficult to be extracted but useful in revealing certain systemic disease. Motivated by the goals of improving detection of such vessels, we propose the radial projection method to locate the vessel centerlines. Then the supervised classification is used for extracting the major structures of vessels. The final segmentation is obtained by the union of the two types of vessels after removal schemes. Our approach is tested on the STARE database, the results demonstrate that our algorithm can yield better segmentation.

Diabetic retinopathy is one of the serious and sight-threatening complications of diabetics. The main symptom of diabetic retinopathy is the presence of exudates that results in yellow flecks due to the fluid that has seeped out of damaged capillaries. This causes the tissue in the retina to distend, resulting in hazy or unclear vision. If they are left untreated, diabetic retinopathy can cause blindness. Hence, segmentation of exudates is vital process in retinal pathologies. The proposed work involves accurate segmentation of exudates from the retinal fundus images. Initially, K-means clustering is applied on the retinal images to separate the exudates and optic disk. Genetic algorithm is used for the accurate segmentation of the exudates in which the fitness function is calculated to perform crossover between the segmented images obtained from the K-means clustering segmentation. Before performing the mutation process, the grayscale image is converted into the RGB channels. These three-segmented channels are further combined by the mutation process to obtain the genetic algorithm output. High-intensity region is determined to be the exudates and the low intensity is said to be the optic disk. The elimination of the optic disk which has the same intensity as that of the exudates is performed using watershed segmentation. Finally, the parameter validation is done after the morphological operations. This method was implemented in 10 images downloaded from CHASE and STARE database and the accuracy has been improved to 94% compared with the existing approaches.

Retinal images play a crucial role in the clinical diagnosis and detection of many eye diseases. However, the retinal image is degraded with noise and suffers from low contrast, which makes it difficult to interpret the image precisely and accurately. So retinal image enhancement becomes a vital step before any further processing. Here, a new approach is suggested for fundus image enhancement, where the image is processed in the spatial domain through an optimal statistical feature‐based transformation function (SFTF). The proposed SFTF has four tunable parameters. An optimal set of these parameters is obtained through a newly suggested adaptive enhanced leader particle swarm optimization technique. The suggested method is investigated with freely accessible DRIVE, STARE, and IDRiD databases. The efficiency of the suggested technique is assessed through different validation indices. The results reveal superior performance compared with other popular methods used for vessel enhancement.

Due to increasing number of diabetic retinopathy cases, ophthalmologists are experiencing serious problem to automatically extract the features from the retinal images. Optic disc (OD), exudates, and cotton wool spots are the main features of fundus images which are used for diagnosing eye diseases, such as diabetic retinopathy and glaucoma. In this paper, a new algorithm for the extraction of these bright objects from fundus images based on marker-controlled watershed segmentation is presented. The proposed algorithm makes use of average filtering and contrast adjustment as preprocessing steps. The concept of the markers is used to modify the gradient before the watershed transformation is applied. The performance of the proposed algorithm is evaluated using the test images of STARE and DRIVE databases. It is shown that the proposed method can yield an average sensitivity value of about 95%, which is comparable to those obtained by the known methods.