Haar Cascade Classifier Research Articles

FITME: BODY MEASUREMENT ESTIMATIONS USING MACHINE LEARNING METHOD

Online shopping platforms have been attracting many customers since they were introduced in the last decade of the 20th century. Using online shopping platforms, customers can purchase any merchandise anywhere and anytime without the need to physically go from store to store to find a product or wait in lines to check out. Despite their advantages in comparison with instore shopping, customers often have concerns when they shop for products that require measurements estimation such as furniture and clothes. Choosing the wrong clothing size, in particular, is a common issue experienced by many online shoppers. Therefore, in this research, we proposed a model that estimates human body measurements from human real-time pictures using Haar Cascade classifier and support vector machines.

Robust facial landmark extraction scheme using multiple convolutional neural networks

Facial landmarks are a set of features that can be distinguished on the human face with the naked eye. Typical facial landmarks include eyes, eyebrows, nose, and mouth. Landmarks play an important role in human-related image analysis. For example, they can be used to determine whether there is a human being in the image, identify who the person is, or recognize the orientation of a face when taking a photograph. General techniques for detecting facial landmarks can be classified into two groups: One is based on traditional image processing techniques, such as Haar cascade classifiers and edge detection. The other is based on machine learning techniques in which landmarks can be detected by training neural network using facial features. However, such techniques have shown low accuracy, especially in some special conditions such as low luminance and overlapped faces. To overcome these problems, we proposed in our previous work a facial landmark extraction scheme using deep learning and semantic segmentation, and demonstrated that with even a small dataset, our scheme could achieve reasonable facial landmark extraction performance under such conditions. Nevertheless, for more extensive dataset, we found several exceptional cases where the scheme could not detect face landmarks precisely. Hence, in this paper, we revise our facial landmark extraction scheme using a deep learning model called Faster R-CNN and show how our scheme can improve the overall performance by handling such exceptional cases appropriately. Also, we show how to expand the training dataset by using image filters and image operations such as rotation for more robust landmark detection.

Menuju Pengenalan Ekspresi Mikro: Pendeteksian Komponen Wajah Menggunakan Discriminative Response Map Fitting

The observations made in the study of micro-expression are to recognize and track the very subtle movements of certain facial areas and in a short time. In this study, the observation of movement is held in some areas of the face component. The facial and facial components detection is the pre-process stage on micro-expression recognition system. The goal at this stage is to get face and face components accurately and quickly on every movement of the video sequence or image sequence. The face landmark point of the Discriminative Response Map Fitting (DRMF) method can be used to get face components area accurately and quickly. This can be done because the facial landmark points used in this model-based method do not change when objects are moved, rotated, or scaled. The results obtained by using this method are accurate with a 100% accuracy value compared to the Haar Cascade Classifier method with an average accuracy of 44%. In addition, the average time required in the formation of facial component boxes for each frame is 0.08 seconds, faster than the Haar Cascade Classifier method of 0.32 seconds. With the results obtained, then the detection of facial components can be obtained accurately and quickly. Furthermore, the boxes of face components obtained are expected to display the appropriate data to be processed correctly and accurately in the next stage, feature extraction and the classification of micro-expression motion stage.

IFRS: An Indexed Face Recognition System Based on Face Recognition and RFID Technologies

Access control systems are in contact with humans in everyday life, it is used in buildings, smartphones, cars, and IoT. Access control systems became an active research area. The performance of an access control system is specified by its speed and accuracy. Biometric systems are powerful access control systems which use humans’ biological or physiological properties to provide access to the restricted data or area. From all of the many biometric system types, the face recognition system is the only type that is delivering the automatic property. Moreover, it is the most acceptable type of biometric systems to the humans. The main challenges in the face recognition system are the degradation of the speed and accuracy when the system database grew bigger. This is because the face recognition system is an identification system that adopts a one to many (1:M) relationship. As a result, there is a need to develop a system with one to one (1:1) relationship, which is a challenging process. Motivated by such challenge, this paper proposes a system called Indexed Face Recognition System (IFRS) which is based on the combination of face recognition technology and Radio Frequency Identification technology. IFRS uses Local Binary Pattern Histogram as a feature vector and Haar-cascade classifier for the face detection. Moreover, the system is enhanced with three pre-processing methods namely: Bilateral filter, Histogram Equalization, and applying Tan and Triggs’ algorithm. In addition, IFRS performs an image normalization processes before and after Face Detection phase to enhance images quality, these process are: Color Conversion and Image Cropping and Resizing. Two experiments were done. The first experiment was done on 400 images with 40 subjects (10 images per subject). The second experiment was done on 210 collected images for 21 subjects (10 images per subject) from University students as a real-life case study. The practical results demonstrates that 4 × 4 image divisions gives better results than 8 × 8 image divisions as far as recognition time, database access time, and storage capacity are concerned. The practical results show that IFRS can reach an accuracy of 100% with a very little amount of time delay that is negligible.

Fatigue Detection Using Raspberry Pi 3

Driver drowsiness is a primary cause of several highway calamities leads to severe physical injuries, loss of money, and loss of human life. The implementation of driver drowsiness detection in real-time will aid in avoiding major accidents. The system is designed for four-wheelers wherein the driver’s fatigue or drowsiness is detected and alerts the person. The proposed method will use 5-megapixel Raspbian camera that captures driver’s face and eyes and processes the images to detect driver’s fatigue. On the detection of drowsiness, the programmed system cautions the driver through an alarm to ensure vigilance. The proposed method constitutes of various stages to determine wakefulness of the driver. According to this output, the warning message is generated. Haar Cascade Classifiers is used to detect the blink duration of the driver and Eye Aspect Ratio (EAR) is calculated. Finally, the alert message along with car plate number is sent to the concerned person mobile with help of Ubidots cloud service and Twilio API. For this Raspberry Pi 3 with Raspbian (Linux Based) Operating System is used.

Real time Implementation of Face Recognition System on Raspberry Pi

Face Recognition is the ability to find and detect a person by their facial attributes. Face is a multi dimensional and thus requires a considerable measure of scientific calculations. Face recognition system is very useful and important for security, law authorization applications, client confirmation and so forth. Hence there is a need for an efficient and cost effective system. There are numerous techniques that are as of now proposed with low Recognition rate and high false alarm rate. Hence the major task of the research is to develop face recognition system with improved accuracy and improved recognition time. Our objective is to implementing Raspberry Pi based face recognition system using conventional face detection and recognition techniques such as A Haar cascade classifier is trained for detection and Local Binary Pattern (LBP) as a feature extraction technique. With the use of the Raspberry Pi kit, we go for influencing the framework with less cost and simple to use, with high performance.

Implementation of security system for bank using open CV and RFID

Security is one of the major concerns in banking sector where we can adapt the latest techniques like face recognition and RFID we can provide better security policies. In this paper we have proposed a model with two major security techniques. The First method provides security for the locker room door by face recognition using OpenCV. Face recognition is a particular type of biometric system that can be used to analyze the obtained information and identify the user uniquely by the trained images. In this proposed model the images of customers are trained. A Microsoft Lifecam HD-3000 is placed outside the locker room. This camera detects the human face using Haar Cascade Classifier and recognizes a customer using LBPH Algorithm. If a trained customer tries to enter then door is unlocked. The customer name is uploaded to cloud. The second method provides security to the cashier cabin by using MFRC522 RFID Module which is very easy to access which consumes less time and more secured compared to the existing system. When an authorized tag is recognized the door is unlocked for certain time period and the userid is uploaded to the cloud. By using these two techniques we can provide security for locker room and cashier cabins in any banking sector.

FACE DETECTION AND RECOGNITION USING HAAR CLASSIFIER AND LBP HISTOGRAM

Facial recognition technology is the process for identifying or verifying a face from digital images. The need for face recognition has been of real importance with the development of modern society. Detection and recognition of faces has been on the rise worldwide owing the requirement for security for economic transactions, authorization, national safety and security and other important factors. The technology comprises of face detection, database creation and face recognition. This paper presents a new approach of face identification using LBP method and Haar-like features. The first step is face detection which is done using Haar cascade classifier. After detection, a face is saved in the database. Then the faces from the database are passed through the face recognition algorithm. The Local Binary Pattern Histogram (LBPH) method is used for face recognition. The performance of face detection can be seen to produce maximum error of 1.6%, 2.1% and 0.8% in case of Real-Time video, image file and video file respectively which may be considered accurate. The recognition algorithm produces maximum error of 0.4% which may be considered accurate as well.

Hybrid Head Tracking for Wheelchair Control Using Haar Cascade Classifier and KCF Tracker

Disability may limit someone to move freely, especially when the severity of the disability is high. In order to help disabled people control their wheelchair, head movement-based control is preferred due to its reliability. This paper proposed a head direction detector framework which can be applied to wheelchair control. First, face and nose were detected from a video frame using Haar cascade classfier. Then, the detected bounding boxes were used to initialize Kernelized Correlation Filters tracker. Direction of a head was determined by relative position of the nose to the face, extracted from tracker’s bounding boxes. Results show that the method effectively detect head direction indicated by 82% accuracy and very low detection or tracking failure.

PENDETEKSIAN OBJEK ROKOK PADA VIDEO BERBASIS PENGOLAHAN CITRA DENGAN MENGGUNAKAN METODE HAAR CASCADE CLASSIFIER

Object detection is a topic widely studied by the scientists as a special study in image processing. Although applications of this topic have been implemented, but basically this technology is not yet mature, futher research is needed to developed to obtain the desired result. The aim of the present study is to detect cigarette objects on video by using the Viola Jones method (Haar Cascade Classifier). This method known to have speed and high accuracy because of combining some concept (Haar features, integral image, Adaboost, and Cascade Classifier) to be a main method to detect objects. In this research, detection testing of cigarettes object is in samples of video with the resolution 160x120 pixels, 320x240 pixels, 640x480 pixels under condition of on 1 cigarette object and condition 2 cigarettes object. The result of this research indicated that percentage of average accuracy highest 93.3% at condition 1 cigarette object and 86,7% in the condition 2 cigarette object that was detected on the video with resolution 640x480 pixels, while the percentage of accuracy lowest 90% at condition 1cigarette object, and 81,7% at the condition 2 cigarette objects, detected on the video with the lowest resolution 160x120 pixels. The percentage of average errors at detection cigarettes object was inversely with percentage of accuracy. So that the detection system is able to better recognize the object of the cigarette, then the number of samples in the database needs to be improved and able to represent various types of cigarettes under various conditions and can be added new parameters related to cigarette object

Boosting Based Implementationof Biometric Authentication in IoT

In security and control application the biometric authentication played a specific and important role to identify the person. Analysis of face recognization is the prerequisite process for the entire authentication. This paper focuses an automatic real-time implementation of face recognization system by highlevel description language such as python. Comparing the biometrics where still images are used, video based biometric holds ample information than a single image. It provides the innovative solution for automatic real time face recognition from the video by the following algorithms like Adaboost, Haar cascade classifier and local binary pattern Histogram (LBPH). From the video stream, the input images are trained by adaboost algorithm which is implemented in cascade classifier. AdaBoost is called as adaptive boosting algorithm. It is a learning algorithm which has been combined with a weak classifier in order to form a strong classifier. Here, the real time testing image is compared with the 627 frames of trained images which are obtained from 47.7 MB (56088648 bytes) video. The hardware implementation of face recognization is obtained and the result can be stored and viewed in http://169.254.108.24. Thus by the above said procedures are authenticated by the combinational performance of Adaboost and Cascade classifier.

Development of a secured room access system based on face recognition using Raspberry Pi and Android based smartphone

Security issues are an important part of everyday life. A vital link in security chain is the identification of users who will enter the room. This paper describes the prototype of a secured room access control system based on face recognition. The system comprises a webcam to detect faces and a solenoid door lock for accessing the room. Every user detected by the webcam will be checked for compatibility with the database in the system. If the user has access rights then the solenoid door lock will open and the user can enter the room. Otherwise, the data will be sent to the master user via Android-based smartphone that installed certain applications. If the user is recognized by the master user, then the solenoid door lock will be opened through the signal sent from the smartphone. However, if the user is not recognized, then the buzzer will alert. The main control circuit on this system is Raspberry pi. The software used is OpenCV Library which is useful to display and process the image produced by webcam. In this paper, we employ Haar Cascade Classifier in an image processing of user face to render the face detection with high accuracy.

Vehicle Classification using Haar Cascade Classifier Method in Traffic Surveillance System

Object detection based on digital image processing on vehicles is very important for establishing monitoring system or as alternative method to collect statistic data to make efficient traffic engineering decision. A vehicle counter program based on traffic video feed for specific type of vehicle using Haar Cascade Classifier was made as the output of this research. Firstly, Haar-like feature was used to present visual shape of vehicle, and AdaBoost machine learning algorithm was also employed to make a strong classifier by combining specific classifier into a cascade filter to quickly remove background regions of an image. At the testing section, the output was tested over 8 realistic video data and achieved high accuracy. The result was set 1 as the biggest value for recall and precision, 0.986 as the average value for recall and 0.978 as the average value for precision.

Sistem Klasifikasi Kendaraan Berbasis Pengolahan Citra Digital dengan Metode Multilayer Perceptron

The evolution of video sensors and hardware can be used for developing traffic monitoring system vision based. It can provide information about vehicle passing by utilizing the camera, so that monitoring can be done automatically. It is needed for the processing systems to provide some information regarding traffic conditions. One such approach is to utilize digital image processing.This research consisted of two phases image processing, namely the process of detection and classification. The process of detection using Haar Cascade Classifier with the training data image form the vehicle and data test form the image state of toll road drawn at random. While, Multilayer Perceptron classification process uses by utilizing the result of the detection process. Vehicle classification is divided into three types, namely car, bus and truck. Then the classification parameters were evaluated by accuracy. The test results vehicle detection indicate the value of accuracy is 92.67. Meanwhile, the classification process is done with phase trial and error to evaluate the parameters that have been determined. Results of the study show the classification system has an average value of the accuracy is 87.60%.

Developing Iris Recognition System for Smartphone Security

Smartphones have become an important way to store sensitive information; therefore, users’ privacy needs to be highly protected. This can be done by using the most reliable and accurate biometric identification system available today: iris recognition. This paper develops and tests an iris recognition system for smartphones. The system uses eye images that rely on visible wavelength; these images are acquired by the smartphone built-in camera. The development of the system passes through four main phases: the first phase is the iris segmentation phase, which is done in three steps to detect the iris region from the captured image, which contains the eye and part of the face using Haar Cascade Classifier training, pupil localization, and iris localization using a Circular Hough Transform. In the second phase, the system applies normalization using a Rubber Sheet model, which converts the iris image to a fixed size pattern. In the third phase, unique features are extracted from that pattern using a Deep Sparse Filtering algorithm. Finally, in the matching phase, seven different matching techniques are investigated to decide the most appropriate one the system will use to verify the user. Two types of testing are conducted: Offline and Online tests. The BIPLab database and a collected dataset are used to measure the accuracy of the system phases and to calculate the Equal Error Rate (EER) for the whole system. The average EER is 0.18 for the BIPLab database and 0.26 for the collected dataset.

Interpretation of sign language into English using NLP techniques

Sign language is a way of communication for deaf & dumb. Different sign recognition techniques are there which are giving output in the form of word for recognized sign. The proposed method is focusing on interpretation of sign language in proper English sentence. Different NLP techniques are used in addition to sign recognition. Input is given as video of sign language followed by framing & segmentation on video. CamShift algorithm is used for tracking & P2DHMM for hand tracking. Haar Cascade classifier is used for sign identification. After sign recognition, the continuous words for respective sign are given as input to POS tagging module. Word net POS tagger is used which is having its own WordNet dictionary. At last LALR parser is used to frame the sentence. In this way proposed sign language interpreter model gives the output in meaningful English sentence & with a goodaccuracy.

Drowsy driver mobile application: Development of a novel scleral-area detection method

A reliable and practical app for mobile devices was developed to detect driver drowsiness. It consisted of two main components: a Haar cascade classifier, provided by a computer vision framework called OpenCV, for face/eye detection; and a dedicated JAVA software code for image processing that was applied over a masked region circumscribing the eye. A binary threshold was performed over the masked region to provide a quantitative measure of the number of white pixels in the sclera, which represented the state of eye opening. A continuously low white-pixel count would indicate drowsiness, thereby triggering an alarm to alert the driver. This system was successfully implemented on: (1) a static face image, (2) two subjects under laboratory conditions, and (3) a subject in a vehicle environment.

DETEKSI KEDIPAN MATA PADA VIDEO MENGGUNAKAN OPEN CV

In the development of technology in the current era is one of the most rapid progress, it is marked by almost all managers of data and information has been done with the computer because of the increasingly diverse information issues handled, Detection of objects is one of the most important early stages before Done object recognition process. Eye blink detection can be used to open a new file or an application. In this research use case detection eye blinking on video using OpenCV to open notepad application. The blink detection uses the haar cascade classifier method for realtime detection and the OpenCV Library. The first step determines the pattern 1111100000. Next enter the video sample avi format to match with a predetermined pattern. In this program the system managed to detect the eye according to the pattern by circling the eye area when the eyes are open or literate and when the eyes closed or brake there is no circle in the eye area for the correct video sample.

An Unobtrusive Computerized Assessment Framework for Unilateral Peripheral Facial Paralysis.

Unilateral peripheral facial paralysis (UPFP) is a form of facial nerve paralysis and clinically classified according to conditions of facial symmetry. Prompt and precise assessment is crucial to neural rehabilitation of UPFP. The prevalent House-Brackmann (HB) grading system relies on subjective judgments with significant interobservation variation. Therefore, to explore an objective method for the UPFP assessment, clinical image sequences are captured using a web camera setup while 5 healthy and 27 UPFP subjects perform a group of predefined actions, including keeping expressionless, raising brows, closing eyes, bulging cheek, and showing teeth in turn. First, facial region is decided using Haar cascade classifier, and then landmark points are acquired by a supervised descent method. Second, these landmark points are used to generate a group of features reflecting the structural parameters of regions of eyebrows, eyes, nose, and mouth, respectively. Third, correlation coefficients are computed between the raw features HB scores. To reduce feature dimensions, only those with correlation coefficients larger than an empirically selected value, 0.35, are input into a support vector machine to generate a classifier. With the classifier, exact match (discrepancy = 0 between result from proposed method and HB scores) rate at 49.9%, and loose match (discrepancy = 1) rate at 87.97% are achieved on the experiment data. After sample augmentation, the final rate is increased to 90.01%, outperformed previous reports. In conclusion, it is demonstrated with an unobtrusive web camera setup, encouraging results have been generated with the proposed framework in this exploratory study.

CHILD AND ADULT CLASSIFICATION USING BIOMETRIC FEATURES BASED ON VIDEO ANALYTICS

As the number of social insecurity in regard to social crimes is on its rise, it requires a CCTV camera a higher accuracy in detecting the objects including pedestrians for efficient work of catching criminals. As the importance of the function of pedestrian detection is socially agreed upon, more studies on image and video based pedestrian detection have been conducted. In terms of that, the goal of this study is classification of pedestrian in two categories as a child and an adult. In this study, Haar cascade classifiers are used. This method first detects a full body and a head. Then, it measures the biometry given the relative proportioning length of a full body and a head. Moving average algorithm is used to obtain threshold ratio. Experimental results show the accuracy 100% for children and 64.5% for adults.