Accurate brain tumor classification from MRI scans is essential for timely and effective diagnosis. Existing deep learning methods, such as Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), achieve high performance but face limitations including high computational cost, overfitting, and limited generalization to diverse clinical data. To address these challenges, this study proposes EffViT-Net, a hybrid CNN-ViT model that combines the feature extraction strength of EfficientNetV2S with the long-range dependency modeling of Vision Transformers. The proposed model was trained and evaluated on a public brain MRI dataset comprising$\mathbf{7, 0 2 3}$labeled images across four tumor classes. Experimental results demonstrate that EffViTNet achieves a classification accuracy of 97.0 %, surpassing conventional CNN and standalone ViT architectures, while maintaining reduced computational complexity. These findings highlight the potential of hybrid CNN-ViT architectures to enhance diagnostic precision, improve model generalization, and support reliable automated medical image analysis.

Handwritten Signature (HS) is a way for verifying the identity of the person. Every person has a unique signature, which is primarily used across various domains such as banking, legal documentation, and digital security. The Signature Verification (SV) is classified into the static method and the dynamic method. The static verification method is dependent on stored images, and the dynamic verification method is dependent on dynamic features of the signature. SV still remains a challenge, particularly in discriminating between genuine signatures and skilled forgeries. Advancement in classification of images using Deep Learning (DL) models has opened an opportunity for this problem. This paper is aimed at studying how signatures can be verified using image processing and DL methods for forgery identification. Our implementation included the use of Siamese Neural Network (SNN) with vision transformer (ViT). The performance of the proposed method was evaluated using CEDAR dataset. The results show that Our suggested model, which combines Vision Transformers (ViT) and Siamese Neural Networks (SNN), verifies signatures using the CEDAR dataset with an accuracy of 99.21%. This exhibits better performance than current techniques, providing high accuracy in differentiating between authentic and fake signatures.

Object detection in agricultural automation is highly crucial in fruit management and optimization of resource utilization. This study conducts an in-depth performance evaluation of YOLO object detection algorithms such as YOLO version 8, YOLO version 9, and YOLO version 10 on identifying and classifying date fruits. Dates are agricultural products that are difficult to differentiate from one another due to their minute variations in color, shape, and texture. Date fruits form the basis of agricultural industries in countries like Saudi Arabia and the Middle East. They differ minimally in some of their physical properties, hence creating difficulties in their classification and sorting processes, which are very important in establishing the quality and edibility of dates harvested. Deep learning techniques are utilized in this work to implement the YOLO algorithm to automate the detection and classification of nine types of date fruits from 1,658 images. Precision and Recall metrics were applied to carefully examine every iteration of the improvement performance of the YOLO model. Among these, YOLO version 9 tends to be the most efficient model, having a Precision of $98.68 \%$, a Recall of 99.06%, with an overall Fitness of 99.5%. These metrics reflect the better capability of YOLO version 9 in sustaining high accuracy over a wide range of detection thresholds. Results prove the potential of YOLO version 9 to improve the efficiency of date fruit production industries by assuring early and correct fruit classification, reducing losses, and increasing productivity.

The rapidly growing field of computer vision holds the promise of transforming numerous aspects of existence, enhancing both quality of life and safety measures. Computer vision also has many applications, one of which is pedestrian detection, which is used in many areas of life such as autonomous driving, monitoring systems, and traffic control. Pedestrian detection algorithms often struggle with many problems such as size variation, varying lighting conditions, or excessive computational execution time, which makes them unsuitable for real-time systems. To address these limitations, this paper proposes an approach that integrates filters with a deep learning model, YOLOv8x. A dataset containing 478 images of walking and sitting poses was utilized to detect pedestrian pose detection. Our model achieved detection fitness and precision of ${9 0 \%}$ for images without pre-processing techniques, and $95 \%$ precision for images after applying a Gaussian filter and with $83 \%$ fitness, and after applying a Laplacian Filter, a precision of ${8 3 \%}$ and fitness of $52 \%$ was obtained. We found that if accuracy is important, applying filters is the best option, and if speed and efficiency are important then pose detection without pre-processing will be efficient.

This study explores the classification of date fruit varieties in the Kingdom of Saudi Arabia using advanced image processing techniques and genotype analysis. Utilizing a unified model with 30 epochs and 640x640 pixel resolution, we achieved a classification accuracy of $99.382 \%$ with both median and Gaussian filters. Notably, misclassifications were observed between Sugaey and Sokari varieties. The training loss exhibited a sharp initial decrease, stabilizing at a low value, while the validation loss showed fluctuations, particularly around the 20th epoch. Top-1 accuracy increased rapidly, reaching near $100 \%$ by epoch 10, with Top- 5 accuracy consistently higher. The low pass and high pass filters demonstrated similar trends, with Top-1 accuracy stabilizing near $90 \%$ and misclassifications predominantly involving the Sugaey variety. These findings underscore the potential of refined image processing techniques to enhance fruit classification, improve crop management, and support genetic enhancement efforts in the date industry, ultimately contributing to economic growth and product quality in Saudi Arabia. From the analysis the following results were obtained. In the median filter, there is a notable misclassification between Sugaey and Sokari. The validation loss decreases but shows some fluctuations, especially around the 20th epoch

A novel Coronavirus disease (COVID-19) is an infectious disease caused by a newly discovered coronavirus. In most cases, the COVID-19 virus spreads primarily through droplets of saliva or discharge from the nose when an infected person coughs or sneezes. Moreover, it specifically targets the patient's respiratory system. To date, there are no specific vaccines or treatments for COVID-19. However, many ongoing clinical trials are evaluating potential therapies. In this paper, we provide a spatial-temporal analysis of the COVID-19 spread in Saudi Arabia as a case study. Two data sets are used and processed, one supplied by the WHO organization and the second from the ministry of health of Saudi Arabia. This study presents a spatial and temporal analysis of the spread of Coronavirus disease (COVID-19) in Saudi Arabia. This kind of viral outbreaks requires early elucidation, understanding its details, clarifying the virus's classification, and its genetic origin for strategic planning, containment, and treatment. In our proposed approach, we use Scatter Plots, Moran Scatter Plots to locate the spread of (COVID-19) on the Saudi Arabia map for spatial analysis. Further, we forecast the spreading using ARIMA (Autoregressive Integrated Moving Average), it is a complex model to estimate regression models in python language. The proposed model shows incredible ability in representing the virus spread pattern with a small error margin of less than 11%.

Aesthetics of photographic images is related to beauty appreciation and is considered vital research in the disciplines of image processing and computer vision. The aesthetic quality of images is a subjective matter and is very challenging to accomplish in order to reach beauty appreciation. Despite the absence of standardization for measuring aesthetic quality, we tried to offer a simple, yet precise, a method to express aesthetic beauty. Aesthetics of photographic images is highly desirable in many applications such as information retrieval applications and others. In this paper, we classify the features of aesthetic images-which are: contrast, noise, blur/focus, image composition, color saturation, image histogram and color harmony-using the Support Vector Machine (SVM) and k-nearest neighbor (KNN) classifiers. After the application of feature extraction and classification processes over images from a video dataset of Atomic Visual Action, classification of the images resulted in two classes: high-aesthetic- quality images and low-aesthetic-quality images. We found that both classifiers gave high accuracy rates, which were relatively close, SVM achieved 86.6667% success rate, while KNN outperformed it with 87.0968% accuracy. On the other hand, the F-score of the SVM was much higher, where SVM gave an F-score of 2, and KNN gave an F-score of 0.

Zika fever is a disease caused by a mosquitoborne virus. In most cases, Zika virus is spread by two species of Aedes mosquito: Ae. aegypti and Ae. albopictus. The first isolation of Zika virus was in Uganda in 1947. Due to the lack of researchers in the past, it was difficult for the scientific community to understand the seriousness of this disease and the ways to reduce its spread. In mid-2015, Zika virus had spread over the Pacific and the Americas. In this research study, we present a spatial and temporal analysis of the spread of Zika virus (ZIKAV) around the world with focus on Saudi Arabia. In our proposed approach, in order to locate the spread of ZIKAV on the world map for spatial analysis we use scatter plots, Moran scatter plots and k-mean clustering. Further, we classify the clustered data using support-vector-machine (SVM) classification. The classification results show high precision and recall scores.

In recent years, facial emotion detection received massive attention because of its applications in computer vision and human-computer interaction fields. Due to the active works in this field, various algorithms and applications were proposed and implemented. In this research, we propose a recommender system for emotion recognition that is capable of detecting the user emotions and suggest a list of appropriate songs that can improve his mood. A brief search was conducted on how music can affect the user mood in short-term to gain knowledge and enable us to provide the users with a list of music tracks that work well on improving the user moods. The proposed system detects the emotions, if the subject has a negative emotion then specific playlist will be presented that contains the most suitable types of music that will improve his mood. On the other hand, if the detected emotion is positive, a suitable playlist will be provided which includes different types of music that will enhance the positive emotions. Implementation of the proposed recommender system is performed using Viola-Jonze algorithm and Principal Component Analysis (PCA) techniques, we were able to implement the proposed system successfully in MATLAB(R2018a).

Recognition of the desert plants is a challenging task for human as well as computers due to the similarities between these plants. We propose a novel method for recognizing of desert plants by the images of the bark. We extract the features of the texture of the bark using Weber Local Descriptor (WLD), we build a dataset of bark images for desert plants, this dataset consists of 1660 bark images for five species of the desert plants, these species are Palm Dates, Mimosa Scabrella, Sidr, Lemon and Pomegranate. We test three classifiers ANN, SVM and KNN on this dataset and the resulted accuracies are 99.7%, 98.8% and 98.0%, respectively. Performance of ANN is very high when compared to SVM and KNN classifiers, hence ANN can be adapted for recognition of the desert plants.