OpenCV Python Research Articles

KUMPAS: A Filipino Sign Language Translator of Deaf and Hearing Individuals Utilizing Computer Vision Algorithm

This study elucidates how the Filipino “Kumpas” translator improves communication between signers and non-signers. Many Hearing people are likely familiar with American Sign Language (ASL), but many are still unaware that the Filipino Deaf have their own unique language called Filipino Sign Language (FSL). In this section, the programmers present a method for bridging the gap between signers and non-signers. Sign to text and speech to sign are the two modes of communication for the “Kumpas” translator. In order to translate using speech, the application would use a speech audio input and based from the words recognized, a 3D character will play a sequence of animations according to the translation. The OpenCV Python library, which is useful for computer vision and image processing tasks, was used by the programmers. MediaPipe has a number of features, including tracking, face recognition, and object detection. The system was tested using an ISO 25010 and based on the evaluation, an overall very satisfactory rating was obtained. Also, findings presented that the system is definitely a useful language translator for Filipinos.

Facial Recognition Based Attendance System with Cloud-Integrated Data Management

Managing attendance at a place where number of people are more is a challenging task, and likely there are few percent chances of error always there. To solve this problem in this paper we have proposed our Face-recognition based attendance system with cloud integrated data management. Another important thing that is having the record of attendance we have used cloud database to store and record attendance. The database is automatically updated by system developed by PyMongo, so that later that can be also displayed to user via their login onto a dashboard. In this project we have built face recognizer with OpenCV python and Eigenfaces algorithm which uses Principal Component Analysis (PCA) and used MongoDB Atlas, a service of Mongo for hosting the cloud database. We will be using MERN stack for building dashboard on which one can monitor their attendance. Using OpenCV against MATLAB also helps in saving memory and gives higher speed of execution

Surveillance System with Human Intrusion Detection

Security in restricted areas is essential for protecting valuable assets, sensitive information, ensuring the safety from intruders. Traditional security systems have many limitations, where they cannot authenticate whether the entered person is an intruder or not. To address this challenge by implementing a real-time face recognition- based surveillance system, is the goal of this project. Realtime Intrusion detection system provides surveillance for restricted and confidential areas with help of face recognition and detection, when an intruder or unauthorized person enters the area, this system will give an alert to the respective in charge through various channels, including email, messaging services, and direct phone calls. In this system, the OpenCV python library along with several algorithms are used to abstract the facial features and to take the input dataset. For face detection, the system utilizes SCRFD and YOLO, and it employs Arcface for accurate face recognition. This technique ensures the system can distinguish between an intruder and an authorized individual entering the secured area. This proactive approach enhances surveillance efficiency and reinforces the safety and integrity of restricted areas. For instance, when an individual enters the restricted area, the system captures and analyses their face. It then verifies whether the detected face matches any authorized faces in the registered user database. If there’s no match, the system identifies the person as an intruder and promptly sends an alert to the designated authority. To enhance accessibility, a user-friendly graphical interface (GUI) has been developed using Python’s Tkinter.

Face Emotion Recognition System for Depression Detection Using AI Techniques

Abstract: The human face is an essential aspect of an individual's body. It plays a crucial function in detecting and identifying emotions since the face is where a person exhibits all of their fundamental emotions. Through human emotions, we solve different types of problems. Like healthcare, security, business, and education. The purpose of this paper is to present the detection of depression in the mental health sector. Depression or stress is faced by most of the population all over the world for many reasons and at different stages of life. As the current human life is a busy life cycle, a person gets depressed or stressed in their daily life. Depression may be found in educational activities, competitive or challenging tasks, employment pressure, family consequences, different sorts of human connection management, health issues, old age, and other situations. Artificial intelligence and deep learning approaches are suggested in this study to assess depression. This research is useful for analyzing the mental health of every employer and psychologist when counselling their patients. Here, we propose a deep convolutional neural network (DCNN) model. This model can classify two types of human facial emotions. Which is based on positive and negative emotions. This model is trained and tested using the FER-2013 dataset. The data set used for experimentation is a FER (Facial Expression Recognition) dataset available in the KAGGLE repository. The implementation environment includes Keras, TensorFlow, and OpenCV Python packages. The result includes the emotion detection accuracy between the training and test phases. The average accuracy achieved was 77%.

Application of Image Processing in Evaluation of Hydraulic Fracturing with Liquid Nitrogen: A Case Study of Coal Samples from Karaganda Basin

Research of microstructure and permeability evolution of coal following LN2 treatment elucidate the process of cryogenic fracturing due to environmentally friendly behavior in comparison with conventional hydraulic fracturing. The evolution of the 2D microstructure of bituminous coal before and after LN2 treatment was examined using a high-resolution camera. The image processing was implemented using functions from the OpenCV Python library that are sequentially applied to digital images of original coal samples. The images were converted into binary pixel matrices to identify cracks and to evaluate the number of cracks, crack density, total crack area, and average crack length. Results were visualized using Seaborn and Matplotlib Python libraries. There were calculations of total crack area (TCA), total number of cracks (TNC), crack density (CD), the average length of cracks (Q2), first (Q1) and third (Q3) quartiles in fracture length statistics. Our findings demonstrate a progressive increase in the Total Crack Area (δTCA) with longer freezing times and an increased number of freezing–thawing cycles. In contrast, the change in crack density (δCD) was generally unaffected by freezing time alone but exhibited a significant increase after several freezing–thawing cycles. Among the freezing times investigated, the highest crack density (CD) value of 300 m−1 was achieved in FT60, while the lowest CD value of 31.25 m−1 was observed in FT90 after liquid nitrogen (LN2) treatment. Additionally, the FTC4 process resulted in a 50% augmentation in the number of cracks, whereas the FTC5 process tripled the number of small cracks.

Cyan Fluorescent Carbon Quantum Dots with Amino Derivatives for the Visual Detection of Copper (II) Cations in Sea Water

Amino- and carboxyl-functionalized carbon quantum dots (Amino-CQDs) were synthesized through fast and simple microwave treatment of a citric acid, ethylenediamine and ethylenediaminetetraacetic acid (EDTA) mix. The reproducible and stable optical properties from newly synthesized CQD dispersion with a maximum absorbance spectra at 330 nm and the symmetric emission maximum at 470 nm made the Amino-CQDs a promising fluorescence material for analytical applications. The highly aminated and chelate moieties on the CQDs was appropriate for a copper (Cu2+) cation sensor in the linear range from 1 × 10-4 mg/mL to 10 mg/mL with a limit of detection at 0.00036 mg/mL by static fluorescence quenching effects. Furthermore, Amino-CQDs demonstrated stable fluorescence parameters for assays in diluted alkali metal solution (Na+ and K+) and sea water. Finally, a visual sensor, based on Amino-CQDs, was successfully created for the 0.01-100 mg/mL range to produce a colorimetric effect that can be registered by computer vision software (Open CV Python).

Animal Classification implemented in Farm fields using CNN

The day-to-day lives of people depend on the food consumed. Even though food is required regularly, people don’t often think of the struggle the farmers face in delivering the food to the market. There are much more criteria to be considered when it comes to the problems affecting the farmers and the fields. One of the most important criteria is the protection of farm fields. Animal intruding the field leads to crop damage, and of course some severe problems that affect the regular profit. Farm fields near mountain slopes are often intruded by wild elephants and wild pigs, that destroy most of the crops and pull down the profit as well as the investment. There are several old methods to protect the field like thorn fences, but those aren’t quite beneficial. The other problem is the classification of animal entering the field. The security features can be adapted only based on the animal that is entering. If the animal intruder is anonymous, preventive measures cannot be immediately taken. The proposed model uses a setup like fence, where cameras are mounted to capture animal movements using OpenCV python. Once any movement is detected, an alert sound goes on, so that people could be aware that some intrusion has occurred. Using image processing by CNN, classification of animal is done by training and testing the dataset. Precautions along with messages to people who could provide help can be implemented as an additional feature to this proposed work. This structure is considered beneficial to be implemented in military bases to capture movements and alert the soldiers.

HYPHAEdelity: a quantitative image analysis tool for assessing peripheral whole colony filamentation.

The yeast Saccharomyces cerevisiae, also known as brewer's yeast, can undergo a reversible stress-responsive transition from individual ellipsoidal cells to chains of elongated cells in response to nitrogen- or carbon starvation. Whole colony morphology is frequently used to evaluate phenotypic switching response; however, quantifying two-dimensional top-down images requires each pixel to be characterized as belonging to the colony or background. While feasible for a small number of colonies, this labor-intensive assessment process is impracticable for larger datasets. The software tool HYPHAEdelity has been developed to semi-automate the assessment of two-dimensional whole colony images and quantify the magnitude of peripheral whole colony yeast filamentation using image analysis tools intrinsic to the OpenCV Python library. The software application functions by determining the total area of filamentous growth, referred to as the f-measure, by subtracting the area of the inner colony boundary from the outer-boundary area associated with hyphal projections. The HYPHAEdelity application was validated against automated and manually pixel-counted two-dimensional top-down images of S. cerevisiae colonies exhibiting varying degrees of filamentation. HYPHAEdelity's f-measure results were comparable to areas determined through a manual pixel enumeration method and found to be more accurate than other whole colony filamentation software solutions.

Evaluation of histogram equalization and contrast limited adaptive histogram equalization effect on image quality and fractal dimensions of digital periapical radiographs.

This study aims to evaluate the effects of histogram equalization (HE) and contrast limited adaptive histogram equalization (CLAHE) on periapical images and fractal dimensions in the periapical region. In this cross-sectional study, digital periapical images were selected from the archive of Dentistry School of Isfahan University of Medical Sciences. The radiographs were taken from mandibular and maxillary anterior single root teeth with healthy root and periodontium. After applying HE and CLAHE algorithms to images, two radiologists evaluated the quality of apex detection from using a 5-point Likert scale (from 5 for very good image quality to 1 for very bad image quality). Afterward, all the images were imported to the ImageJ application, and the region of interest (ROI) was specified as the region between the two central incisors. The fractal box-counting method was used to determine fractal dimensions (FD) values. Nonparametric Wilcoxon-Friedman test, Intraclass Correlation Coefficient test, T-test, and Pair T-test were performed as statistical analysis (α = 0.05). Fifty-three radiographs were analyzed and the image quality assessments were significantly different between raw images and images after performing HE, CLAHE (p value < 0.001), and using CLAHE algorithm significantly increases image quality assessments more than HE (p value = 0.009). There was a significant difference in FD values for images after applying CLAHE and HE compared to raw images (p value < 0.001), and HE decreased the FD value significantly more than CLAHE (p value = 0.019). Employing CLAHE and HE algorithm via OpenCV python library improves the periapical image quality, which is more significant using the CLAHE algorithm. Moreover, applying CLAHE and HE reduces trabecular bone structure detection and FD values in periapical images, especially in HE.

Video-Based Detection, Counting and Classification of Vehicles Using OpenCV

In this era people using vehicles is getting increased day by day. To plan, monitor and also controlling of these vehicles is becoming a big challenge. A system is to be implemented without altering the infrastructure, so a video- based vehicle capturing and analysis of that video without affecting the traffic is required, by which traffic accidents and congestion can be determined. In this paper, we have come up with a solution for the above problem using the video surveillance considering the video data from the traffic cameras. We have used adaptive thresholding method, Gaussian based background subtraction with tracking methods such as blob tracking and virtual detector. The implementation was done using OpenCV Python as a tool. Our proposed system can identify, track the congestion and help in counting the objects precisely.

"Wheelchair Movement through Eyeball Recognition using Raspberry Pi "

We all consider how we might help people who are in needy, whether economically or substantially. As a graduate, on the other hand, allows us to create a new instrument or machine that benefits the less fortunate. This project is an example of how we can make a difference in society. Many people have become paralyzed in recent years. Paralysis is nothing but a complete loss of power in muscle group. In the bad scenario, the disable could only operate his eyes. To assist these disabled people, we are implementing the project eyeball movement-based wheelchair would benefit them the most. In comparison to previous automated wheelchairs, this would be more accurate because noise from the outside environment causes inaccuracy in voice-controlled wheelchairs, and human effort is necessary for a head movement-based wheelchair. Here we are putting in place a device that allows people sitting in wheelchairs and look straight into the camera to direct the wheelchair in the desired path easily by looking in that specific path. We designed this system using Raspberry Pi (with image processing, camera, OpenCV python). It involves certain set of algorithms that allows you to run the wheelchair. To control the wheelchair movement a method is proposed that is called Eyeball Localization. To reduce the cost and computational complexity, there is an algorithm designed with efficient system and different executional steps. An Open CV application monitors the camera signals and directs the motor connected to the Raspberry Pi microprocessor via the serial interface to move in a specific path. Because the system is economically handy, it can be used by patients from a wide range of socioeconomic backgrounds. When compared to other automated wheelchairs, this would be more accurate.

DRONE HUNTER AND FIRE USE FIRE EXTINGUISHER BALL-BASED IMAGE PROCESSING AND MACHINE LEARNING METHODS

Burning activities are still common in Indonesia, but the handling by the government has not been able to maximize performance in extinguishing fires that are difficult to achieve with standard equipment. The drone that the author developed is named Zerologic which is designed to use a remote monitoring system with machine learning algorithms and image processing methods in finding hotspots using a webcam camera. This camera sends object data which is then processed on the Raspberry Pi 4 using the OpenCV Python software. Besides being designed to search for hotspots, this drone can also minimize the spread of smoke by using a fire extinguisher ball that functions as a fire extinguisher that will be carried directly by the drone. ZEROlogic drones are useful for making it easier for forest firefighters to handle forest fires by finding and extinguishing hotspots that are difficult to reach by humans. In addition to being able to search for and search for fire, this drone ZEROlogic goes directly to the hotspots.&#x0D; &#x0D; Keywords: Drone; Fire Extingusher Ball; Image Processing; Machine Learning

Colour discernment of tomatoes using machine vision system with OpenCV Python and Raspberry Pi

Colour is the first quality attribute of food that consumers examine and it is an important component of food quality that influences market acceptance. Classification of fruits by visual inspection is an arduous, time-consuming process and prone to human error. The machine vision system is a distributed control system that integrates several machine vision modules with a control module and a user interface unit. This research proposes a method for recognising and sorting tomato fruits into a preferred location continuously. Before designing colour sorter the physical properties of fruits were studied. The major and minor diameter of the tomatoes ranges from 45-60mm and 35-50mm, respectively. The mean geometric diameter, sphericity and surface area were 48.64mm,0.94 and 6477.14mm2 respectively. The average length, width, thickness, bulk density and true density were 54.63mm, 48.44mm, 51.42mm, 0.6874g/cm3 , 0.9852g/cm3 , respectively. The colour sorter was researched, designed and created with Raspberry Pi, USB camera, servo motor and different digital as well as mechanical components. The model used for Raspberry Pi is Raspberry Pi 3 Model B+, USB camera with a video resolution of 640 x 480, 4.2-6V servo motor. Image evaluation is completed on each captured picture and Raspberry Pi will do the selection of which fruit can be sorted. Specific programming code in Python is written for this system. The developed colour sorter captures images and diverts fruits into the respective channel at the rate of 1800 fruits/h (i.e.one fruit per 2 seconds).

Automated progress monitoring of construction projects using Machine learning and image processing approach

Project progress tracking and controlling is one of the most critical responsibilities of construction project management. Current practices for forecasting the effectiveness of a construction project include an evaluation that is still laborious, long-drawn-out, and can prone to errors. Digitalization has a tremendous potential to enhance management practices in the field of construction. The building sector has been reluctant to admit new technology. This points out the importance of an automated method for tracking the progress of projects. The goal of this research is to implement a monitoring system for Construction Progress Tracking (CPT). Machine learning and image processing techniques are used to ensure CPT automatically. In particular, masonry activity in construction is focused, though it can be broadened to other construction work. The proposed deep learning model is trained using a set of data of 356 images taken from several worksites and websites. The proposed system is demonstrated with OpenCV Python language and an automated progress report is generated in Microsoft excel. The study developed a platform for automated building project progress monitoring. It has also built a systematic strategy for gathering the standardized dataset for benchmarking purposes. The following are some of the study's notable findings: A supervised CNN classifier was constructed for brickwork recognition using spatial and color information. The classifier worked well, with accuracy and recall values of 81% and 83%, respectively. A uniform collection of 356 photos was created. This resulted in the creation of a benchmarked dataset for a masonry wall. The achieved results reveal high precision and speed to effectively detect the construction project without the interference of human activities, thereby facilitating improved inspection and supervision.

Methods of Vehicle Recognition and Detecting Traffic Rules Violations on Motion Picture Based on OpenCV Framework

In this era, people using vehicles is getting increased day by day. As pedestrians leading a dog for a walk, or hurrying to their workplace in the morning, we’ve all experienced unsafe, fast-moving vehicles operated by inattentive drivers that nearly mow us down. Many of us live in apartment complexes or housing neighborhoods where ignorant drivers disregard safety and zoom by, going way too fast. To plan, monitor and also control these vehicles is becoming a big challenge. In the article, we have come up with a solution to the above problem using the video surveillance considering the video data from the traffic cameras. Using computer vision and deep learning technology we will be able to recognize violations of rules. This article will describe modern CV and DL methods to recognize vehicle on the road and traffic violations of rules by them. Implementation of methods can be done using OpenCV Python as a tool. Our proposed solution can recognize vehicles, track their speed and help in counting the objects precisely.

X-ray Image Recognition Method for Crimping Defects of Strain Clamp Based on OpenCV

The crimp quality of the tension clamp of the line affects the safety of the power grid. At present, the measurement of the quality of the tension clamp has certain limitations. An X-ray image detection method for strain clamp based on image processing technology is proposed. Firstly, the X-ray image of the strain clamp is taken and the image is preprocessed. Secondly, by selecting the defect part image of the typical defect sample, using some statements of OpenCV Python Library in Python to quickly identify and detect other X-ray pictures, and mark the defect part of other pictures. Finally, whether it is a defect is determined according to the cumulative value image of the gray value distribution of the marked defect area. Through the research in this paper, the rapid identification of the X-ray image of the crimping position of the tension clamp can be realized, which has important reference value for the engineering application of the crimping quality inspection of the tension clamp.

Real Time Moving Vehicle Congestion Detection and Tracking using OpenCV

In this era people using vehicles is getting increased day by day. To plan, monitor and also controlling of these vehicles is becoming a big challenge. A system is to be implemented without altering the infrastructure, so a video- based vehicle capturing and analysis of that video without affecting the traffic is required, by which traffic accidents and congestion can be determined. In this paper, we have come up with a solution for the above problem using the video surveillance considering the video data from the traffic cameras. We have used adaptive thresholding method, Gaussian based background subtraction with tracking methods such as blob tracking and virtual detector. The implementation was done using OpenCV Python as a tool. Our proposed system can identify, track the congestion and help in counting the objects precisely.

Content‐based image retrieval using Gaussian–Hermite moments and firefly and grey wolf optimization

Rapid growth in the transfer of multimedia information over the Internet requires algorithms to retrieve a queried image from large image database repositories. The proposed content-based image retrieval (CBIR) uses Gaussian–Hermite moments as the low-level features. Later these features are compressed with principal component analysis. The compressed feature set is multiplied with the weight matrix array, which has the same size as the feature vector. Hybrid firefly and grey wolf optimization (FAGWO) is used to prevent the premature convergence of optimization in the firefly algorithm. The retrieval of images in CBIR is carried out in an OpenCV python environment with K-nearest neighbours and random forest algorithm classifiers. The fitness function for FAGWO is the accuracy of the classifier. The FAGWO algorithm derives the optimum weights from a randomly generated initial population. When these optimized weights are applied, the proposed algorithm shows better precision/recall and efficiency than other techniques such as exact legendre moments, Region-based image retrieval, K-means clustering ​and Color descriptor wavelet-based texture descriptor retrieval technique. In terms of optimization, hybrid FAGWO outperformed various optimization techniques (when used alone) like Particle Swarm Optmization, Genetic Algorithm, Grey-Wolf Optimization and FireFly algorithm.

Face Recognition System using Micro Unmanned Aerial Vehicle

With the price of UAV or people often call Drone getting cheaper, making this technology can be enjoyed not only for limited communities but also for the general public. The camera features mounted on the drone can be used for face detection and recognition. In this paper, we implement Haar-Cascade based classifier for face detection and recognition using OpenCV Python on a micro UAV that only 34.7 gr weight. The face detection process is done in real-time using an FPV camera that is controlled indoors at a distance of less than 50m. From the results of the experiment, it appears that the angle of the face is very influential, especially on the face that is not fully open, like a woman who wears a hijab. The best angle to take is in the position of flying in front of the face in accordance with the slope of the FPV camera mounted on the micro UAV.

A Smart Transportation Design System for Restricted Areas with Vehicle Automation Technologies using Raspberry Pi B and Open CV Python – An Experimental Approach

With the advent of sensors and automation technologies, the intelligent transportation system has become a horizon in energizing and transforming human lives. It gains attraction among various communities due to its reduced workforce and efficient automation. In recent decades, digital advancements stood witnessed as the novel technology in performing the traffic control regime. However, factors such as over speed, natural disasters, and human distractions making the traffic system more puzzling. Hence to address the challenges, the proposed system propounds the novel way of traffic control by taking the vehicle over-speed as the intended factor. It performs automatic control of vehicle speed to avoid accidents and to accomplish safe driving in restricted areas. In this system, Raspberry Pi B microcontroller is utilized to embrace the detection of traffic signals. Additionally, the ultrasonic sensor is equipped for measuring the distance of the vehicles ahead to it in order to avoid collisions. Moreover, the R-pi camera module is employed for the detection of traffic signals and signboards. The real-world images are processed using Open CV python for object and traffic sign detection. Typically, it performs some intelligent classification of the images acquired from the camera module. Furthermore, the speed control of the vehicle is facilitated by the deployment of DC motors connected to the engine. Thus, the proposed system is designed to achieve the speed control and automation of the vehicle as per the warning signals. Here, python has used for programming the microcontroller. Also, step by step analysis of the system is carried out, and the experimental results are shown to visualize the function of the proposed self-automated vehicle.