The Feasibility of Haar Feature-Based Endoscopic Ultrasound Probe Tracking for Implanting Hydrogel Spacer in Radiation Therapy for Pancreatic Cancer

PurposeWe proposed a Haar feature-based method for tracking endoscopic ultrasound (EUS) probe in diagnostic computed tomography (CT) and Magnetic Resonance Imaging (MRI) scans for guiding hydrogel injection without external tracking hardware. This study aimed to assess the feasibility of implementing our method with phantom and patient images.Materials and MethodsOur methods included the pre-simulation section and Haar features extraction steps. Firstly, the simulated EUS set was generated based on anatomic information of interpolated CT/MRI images. Secondly, the efficient Haar features were extracted from simulated EUS images to create a Haar feature dictionary. The relative EUS probe position was estimated by searching the best matched Haar feature vector of the dictionary with Haar feature vector of target EUS images. The utilization of this method was validated using EUS phantom and patient CT/MRI images.ResultsIn the phantom experiment, we showed that our Haar feature-based EUS probe tracking method can find the best matched simulated EUS image from a simulated EUS dictionary which includes 123 simulated images. The errors of all four target points between the real EUS image and the best matched EUS images were within 1 mm. In the patient CT/MRI scans, the best matched simulated EUS image was selected by our method accurately, thereby confirming the probe location. However, when applying our method in MRI images, our method is not always robust due to the low image resolution.ConclusionsOur Haar feature-based method is capable to find the best matched simulated EUS image from the dictionary. We demonstrated the feasibility of our method for tracking EUS probe without external tracking hardware, thereby guiding the hydrogel injection between the head of the pancreas and duodenum.

Facial Recognition on System Prototype to Verify Users using Eigenface, Viola-Jones and Haar

Facial recognition is one of the most popular way to authenticate user into a system. This method is preferable considering the tendency of users for using the same password across multiple sites which made the user has already made his own account securities in vulnerable states. Using biometrics might supply solutions to solve this problem and facial recognition is one of the best biometric methods can be apply as a digital account security solution. This study to design a prototype system implementing facial recognition to verify users to measure how accurate these methods are. The method used here is Viola-Jones for face detection, Eigenface and Haar feature for face recognition from the OpenCV. The system was designed in Java. Based on the test results from the system designed, system can recognize user face with 100% accuracy if faces are shot in a well desirable condition. The system is able to recognize the user's face with various expressions including with or without glasses. However, the system has difficulty in recognizing user’s face in facing up, down, sideways position or blocked by accessories or body parts such as hands. After some experiment, it was proven that the system designed is accurate, reliable and safe enough to be implemented to digital authorization process.

The Viola-Jones Face Detection Algorithm Analysis: A Survey

In this paper, we analysis the Viola-Jones algorithm, the most real-time face detection system has been used. It is consisting from three main concepts to enable a robust detection: the integral image for Haar feature computation, Adaboost for selecting feature and cascade to make resource allocation more efficient. Here we propose each stage starting from Integral image to the end with Cascading and some of algorithmic description for stages. The Viola-Jones algorithm gives multiple detections, a post-processing step which reduce detection redundancy using Adaboost and cascading.

A Real Time Image Processing Bird Repellent System Using Raspberry Pi

Rice is one of the most consumed foods in Nigeria, therefore it’s production should be on the high as to meet the demand for it. Unfortunately, the quantity of rice produced is being affected by pests such as birds on fields and sometimes in storage. Due to the activities of birds, an effective repellent system is required on rice fields. The proposed effective repellent system is made up of hardware components which are the raspberry pi for image processing, the servo motors for rotation of camera for better field of view controlled by Arduino connected to the raspberry pi, a speaker for generating predator sounds to scare birds away and software component consisting of python and Open Cv library for bird feature identification. The model was trained separately using haar features, HOG (Histogram of Oriented Gradients) and LBP (Local Binary Patterns).Haar features resulted in the highest accuracy of 76% while HOG and LBP were, 27% and 72% respectively. Haar trained model was tested with two recorded real time videos with birds, the false positives were fairly low, about 41%. This haar feature trained model can distinguish between birds and other moving objects unlike a motion detection system which detects all moving objects. This proposed system can be improved to have a higher accuracy with a larger data set of positive and negative images. Keywords—Electronic pest repeller Haar cascade classifier, ultrasonic

Biometric for Cattle Identification using Muzzle Patterns

Similar to human biometrics such as faces and fingerprints, animals also have biometrics for individual identifiers. This research paper works on biometrics of cattle using images of muzzle patterns. The proposed approach begins with a training process to construct a cattle face localization model using a Haar feature-based cascade classifier. Then, the watershed technique is applied to segment a region of interest (RoI) of a muzzle area in the detected region of the cattle face. This muzzle ROI is further enhanced to make ridge lines more outstanding. The next step, using two approaches, is to extract a main feature descriptor based on a bag of histograms of oriented gradients (BoHoG) and a histogram of local binary patterns (LBP). Then, the support vector machine (SVM) is applied with the histogram intersection kernel for a final cattle identifier. The proposed method is evaluated using five different datasets including one existing cattle dataset used in previous research works, one newly collected dataset of swamp buffalo captured in a controlled environment, and three newly collected datasets of swamp buffalo captured in an outdoor field environment. This outdoor field environment includes challenges of freely moving cattle and differences in daylight. It could achieve a promising accuracy of 95% for a large dataset of 431 subjects.

A Novel Changing Athlete Body Real-Time Visual Tracking Algorithm Based on Distractor-Aware SiamRPN and HOG-SVM

Athlete detection in sports videos is a challenging task due to the dynamic and cluttered background. Distractor-aware SiamRPN (DaSiamRPN) has a simple network structure and can be utilized to perform long-term tracking of large data sets. However, similarly to the Siamese network, the tracking results heavily rely on the given position in the initial frame. Hence, there is a lack of solutions for some complex tracking scenarios, such as running and changing of bodies of athletes, especially in the stage from squatting to standing to running. The Haar feature-based cascade classifier is involved to catch the key frame, representing the video frame of the most dramatic changes of the athletes. DaSiamRPN is implemented as the tracking method. In each frame after the key frame, a detection window is given based on the bounding box generated by the DaSiamRPN tracker. In the new detection window, a fusion method (HOG-SVM) combining features of Histograms of Oriented Gradients (HOG) and a linear Support-Vector Machine (SVM) is proposed for detecting the athlete, and the tracking results are updated in real-time by fusing the tracking results of DaSiamRPN and HOG-SVM. Our proposed method has reached a stable and accurate tracking effect in testing on men’s 100 m video sequences and has realized real-time operation.