An Efficient System for Automatic Blood Type Determination Based on Image Matching Techniques

This paper presents a fast and accurate system to determine the type of blood automatically based on image processing. Blood type determination is important in emergency situations, where there is a need for blood transfusion to save lives. The traditional blood determination techniques are performed manually by a specialist in medical labs, where the result requires a long time or may be affected by human error. This may cause serious consequences or even endanger people’s lives. The proposed approach performs blood determination in real-time with low cost using any available mobile device equipped with a camera. A total of 500 blood samples were processed in this study using different image matching techniques including oriented fast and rotated brief (ORB), scale invariant feature transform (SIFT), and speed-up robust feature (SURF). The evaluation results show that our proposed system, which adopts the ORB algorithm, is the fastest and the most accurate among the state-of-the-art systems. It can achieve an accuracy of 99.6% in an average time of 250 ms.

Development of Speed Up Robust Feature Algorithm for aerial image feature extraction

Speed Up Robust Feature Algorithm (SURF) has been a very useful technique in the advancement of image feature algorithm. The strategy offers an extremely decent agreement between the runtime and accuracy, especially at object borders and fine structures. It has a wide scope of applications in remote sensing like getting computerized surface models from UAV and satellite images. In this paper, SURF algorithm has been discussed in details to enhance the capability of the system for image feature extraction technique to detect and obtain the maximum feature points from aerial imagery. The algorithms are developed depending upon such phenomena in which a maximum result can be obtained in very less time.

Superpixel-Based Feature Tracking for Structure from Motion

Feature tracking in image collections significantly affects the efficiency and accuracy of Structure from Motion (SFM). Insufficient correspondences may result in disconnected structures and incomplete components, while the redundant correspondences containing incorrect ones may yield to folded and superimposed structures. In this paper, we present a Superpixel-based feature tracking method for structure from motion. In the proposed method, we first propose to use a joint approach to detect local keypoints and compute descriptors. Second, the superpixel-based approach is used to generate labels for the input image. Third, we combine the Speed Up Robust Feature and binary test in the generated label regions to produce a set of combined descriptors for the detected keypoints. Fourth, the locality-sensitive hash (LSH)-based k nearest neighboring matching (KNN) is utilized to produce feature correspondences, and then the ratio test approach is used to remove outliers from the previous matching collection. Finally, we conduct comprehensive experiments on several challenging benchmarking datasets including highly ambiguous and duplicated scenes. Experimental results show that the proposed method gets better performances with respect to the state of the art methods.

Maize Leaf Disease Image Classification Using Bag of Features

Image classification is an image grouping based on similarities features. The features extraction stage is a crucial factor for classifying an image. In the conventional image classification, the features commonly used are morphology, color, and texture with various derivative features. The type and number of appropriate features will affect the classification results. In this study, image classification by using the Bag of Features (BOF) method which can generate features automatically. It consists of 4 stages: feature point location by using grid method, feature extraction by using Speed Up Robust Feature (SURF), clustering word-visual vocabularies by using k-means, and classification by using Support Vector Machine (SVM). The classification data are maize leaf images from the PlantVillage-Dataset. The data consists of 3 types of images: RGB, grayscale and segmentation images. Each type includes four classes: healthy, Cercospora, common rust, and northern leaf blight. There are 50 images for each class. We used two scenarios of testing for each type of data: training and validation, 70% and 80% images for training, and the rest for validation. Experimental results showed that the validation accuracies of RGB, grayscale, and segmentation images were 82%, 77%, and 85%.

KLASIFIKASI KATEGORI CITRA DIGITAL DENGAN METODE BAG OF VISUAL WORDS

The human eye can distinguish objects from digital images, however, computers do not have the ability as human eyes that can directly distinguish objects from digital images. Therefore the bag of visual words method was created. Bag of visual words is a method for presenting digital images based on local features. Bag of visual words illustrates how an image can be taken its characteristics, so that computers can distinguish objects on digital images. The test results show that the bag of visual words are still not maximal in classifying digital image categories, especially the chair category, which is only able to produce the most accurate accuracy of 75%. To improve the performance quality of bag of visual words in classifying digital image categories, especially the chair category, you can add an approach to determine the good number of K in clustering the visual words pattern. Keywords: Bag Of Visual Words, Classification, Digital Image, Speed-Up Robust Feature, Support Vector Machine Abstrak: Secara kasat mata manusia bisa membedakan objek pada citra digital, namun, komputer tidak memiliki kemampuan sebagai mata manusia yang dapat secara langsung membedakan objek pada citra digital. Maka dari itu diciptakanlah metode bag of visual words. Bag of visual words adalah metode untuk menyajikan citra digital berdasarkan fitur lokal. Bag of visual words menggambarkan bagaimana suatu gambar dapat diambil karakteristiknya, sehingga komputer dapat membedakan objek pada citra digital. Hasil pengujian menunjukkan bag of visual words masih belum maksimal dalam mengklasifikasi kategori citra digital khususnya kategori chair, yang hanya mampu menghasilkan akurasi paling akurat sebesar 75 %. Untuk meningkatkan kualitas kinerja bag of visual words dalam mengklasifikasi kategori citra digital khususnya kategori chair, dapat menambahkan pendekatan untuk menentukan jumlah K yang baik dalam mengkluster pola visual words. Kata kunci: Bag Of Visual Words, Klasifikasi, Citra Digital, Speed-Up Robust Feature, Support Vector Machine

Writer Identification Based on Arabic Handwriting Recognition by using Speed Up Robust Feature and K- Nearest Neighbor Classification

In a writer recognition system, the system performs a “one-to-many” search in a large database with handwriting samples of known authors and returns a possible candidate list. This paper proposes method for writer identification handwritten Arabic word without segmentation to sub letters based on feature extraction speed up robust feature transform (SURF) and K nearest neighbor classification (KNN) to enhance the writer's identification accuracy. After feature extraction, it can be cluster by K-means algorithm to standardize the number of features. The feature extraction and feature clustering called to gather Bag of Word (BOW); it converts arbitrary number of image feature to uniform length feature vector. The proposed method experimented using (IFN/ENIT) database. The recognition rate of experiment result is (96.666).

Content-Aware Retargeted Image Quality Assessment

In targeting the low correlation between existing image scaling quality assessment methods and subjective awareness, a content-aware retargeted image quality assessment algorithm is proposed, which is based on the structural similarity index. In this paper, a similarity index, that is, a local structural similarity algorithm, which can measure different sizes of the same image is proposed. The Speed Up Robust Feature (SURF) algorithm is used to extract the local structural similarity and the image content loss degree. The significant area ratio is calculated by extracting the saliency region and the retargeted image quality assessment function is obtained by linear fusion. In the CUHK image database and the MIT RetargetMe database, compared with four representative assessment algorithms and other latest four kinds of retargeted image quality assessment algorithms, the experiment proves that the proposed algorithm has a higher correlation with Mean Opinion Score (MOS) values and corresponds with the result of human subjective assessment.