Clinical treatment of skin lesion is primarily dependent on timely detection and delimitation of lesion boundaries for accurate cancerous region localization. Prevalence of skin cancer is on the higher side, especially that of melanoma, which is aggressive in nature due to its high metastasis rate. Therefore, timely diagnosis is critical for its treatment before the onset of malignancy. To address this problem, medical imaging is used for the analysis and segmentation of lesion boundaries from dermoscopic images. Various methods have been used, ranging from visual inspection to the textural analysis of the images. However, accuracy of these methods is low for proper clinical treatment because of the sensitivity involved in surgical procedures or drug application. This presents an opportunity to develop an automated model with good accuracy so that it may be used in a clinical setting. This paper proposes an automated method for segmenting lesion boundaries that combines two architectures, the U-Net and the ResNet, collectively called Res-Unet. Moreover, we also used image inpainting for hair removal, which improved the segmentation results significantly. We trained our model on the ISIC 2017 dataset and validated it on the ISIC 2017 test set as well as the PH² dataset. Our proposed model attained a Jaccard Index of 0.772 on the ISIC 2017 test set and 0.854 on the PH² dataset, which are comparable results to the current available state-of-the-art techniques.

Agriculture has become an essential field of study and is considered a challenge for many researchers in computer vision specialization. The early detection and classification of plant diseases are crucial for preventing growing diseases and hence yield reduction. Although many state-of-the-artwork proposed various classification techniques for plant diseases, still face many challenges such as noise reduction, extracting the relevant features, and excluding the redundant ones. Recently, deep learning models are noticeable as hot research and are widely used for plant leaf disease classification. Although the achievement with these models is notable, still the need for efficient, fast-trained, and few-parameters models without compromising on performance is inevitable. In this work, two approaches of deep learning have been proposed for Palm leaf disease classification: Residual Network (ResNet) and transfer learning of Inception ResNet. The models make it possible to train up to hundreds of layers and achieve superior performance. Considering the merit of their effective representation ability, the performance of image classification using ResNet has been boosted, such as diseases of plant leaves classification. In both approaches, problems such as variation of luminance and background, different scales of images, and inter-class similarity have been treated. Date Palm dataset having 2631 colored images with varied sizes was used to train and test the models. Using some well-known metrics, the proposed models outperformed many of the recent research in the field in original and augmented datasets and achieved an accuracy of 99.62% and 100% respectively.

Content-based image medical retrieval (CBMIR) is a technique for retrieving medical images on the basis of automatically derived image features such as colour, texture and shape. There are many applications of CBMIR, such as teaching, research, diagnosis and electronic patient records. The retrieval performance of a CBMIR system depends mainly on the representation of image features, which researchers have studied extensively for decades. Although a number of methods and approaches have been suggested, it remains one of the most challenging problems in current (CBMIR) studies, largely due to the well-known "semantic gap" issue that exists between machine-captured low-level image features and human-perceived high-level semantic concepts. There have been many techniques proposed to bridge this gap. This study proposes a novel relevance feedback retrieval method (RFRM) for CBMIR. The feedback implemented here is based on voting values performed by each class in the image repository. Here, eighteen using colour moments and GLCM texture features were extracted to represent each image and eight common similarity coefficients were used as similarity measures. After briefly researching using a single random image query, the top images retrieved from each class are used as voters to select the most effective similarity coefficient that will be used for the final searching process. Our proposed method is implemented on the Kvasir dataset, which has 4,000 images divided into eight classes and was recently widely used for gastrointestinal disease detection. Intensive statistical analysis of the results shows that our proposed RFRM method has the best performance for enhancing both recall and precision when it uses any group of similarity coefficients.

During the last decade a huge amount of data have been shown and introduced in the Internet. Recommender systems are thus predicting the rating that a user would give to an item. Collaborative filtering (CF) techniques are the most popular and widely used by recommender systems technique, which utilize similar neighbors to generate recommendations. This paper provides the concepts, methods, applications and evaluations of the CF based on the literature review. The paper also highlights the discussion of the types of the recommender systems as general and types of CF such as; memory based, model based and hybrid model. In addition, this paper discusses how to choose an appropriate type of CF. The evaluation methods of the CF systems are also provided throughout the paper.