71 skills found · Page 1 of 3
facebookresearch / SentAugmentSentAugment is a data augmentation technique for NLP that retrieves similar sentences from a large bank of sentences. It can be used in combination with self-training and knowledge-distillation, or for retrieving paraphrases.
zegami / Image Similarity ClusteringThis project allows images to be automatically grouped into like clusters using a combination of machine learning techniques.
bitsmuggler / Arc42 C4 Software Architecture Documentation ExampleThis example shows how you can use arc42 in combination with the C4 model and the Documentation as Code technique.
udacity / AIND CV FacialKeypointsAIND, computer vision capstone project. This repo contains starting code for an end-to-end facial keypoint recognition system that relies on a combination of computer vision and deep learning techniques.
TheWiselyBearded / Sbs GeneratorThis repository contains a framework for converting monocular videos into side-by-side (SBS) 3D videos. It utilizes a combination of image processing techniques and depth map predictions to generate separate views for each eye, creating a 3D effect when viewed with appropriate hardware.
Offensive-Panda / DV NEWThis is the combination of multiple evasion techniques to evade defenses. (Dirty Vanity)
babdulhakim2 / Financial Analysis With LlmThe application uses a combination of natural language processing (NLP), and financial analysis techniques to extract, process, and analyze data from uploaded financial documents (Excel format). It provides insights such as transaction summaries, suspicious trends, cash deposit detection, entity recognition, and potential ML/TF activities.
ShaharKatz / Caffe Data Augmentationa branc caffe with feature of Data Augmentation using a configurable stochastic combination of 7 data augmentation techniques.
LeadingIndiaAI / Fake News Detection Fake news is misinformation or manipulated news that is spread across the social media with an intention to damage a person, agency and organisation. Due to the dissemination of fake news, there is a need for computational methods to detect them. Fake news detection aims to help users to expose varieties of fabricated news. To achieve this goal, first we have taken the datasets which contains both fake and real news and conducted various experiments to organize fake news detector. We used natural processing, machine learning and deep learning techniques to classify the datasets. We yielded a comprehensive audit of detecting fake news by including fake news categorization, existing algorithms from machine learning techniques. In this project, we explored different machine learning models like Naïve Bayes, K nearest neighbors, decision tree, random forest and deep learning networks like Shallow Convolutional Neural Networks (CNN), Deep Convolutional Neural Network (VDCNN), Long Short-Term Memory Network (LSTM), Gated Recurrent Unit Network (GRU), Combination of Convolutional Neural Network with Long Short-Term Memory (CNN-LSTM) and Convolutional Neural Network with Gated Recurrent Unit (CNN-LSTM).
wandahangFY / SimOTMBy converting single-channel grayscale images into multi-channel images through various data enhancement techniques, SimOTM enhances the detection capabilities of object detection models without complex manual design or combination requirements.
aymane-maghouti / Big Data ProjectThis project aims to predict smartphone prices using a combination of batch and stream processing techniques in a Big Data environment. The architecture follows the Lambda Architecture pattern, providing both real-time and batch processing capabilities to users.
ankitVP77 / Blind Motion Deblurring For Legible License Plates Using Deep LearningThis project deals with blind motion deblurring using a combination of Weiner Deconvolution and Deep Learning techniques to estimate the length and angle parameter of the Point-Spread Function
bglover / MastercrackA PHP class to calculate the combination for a masterlock using a technique discovered by Samy Kamkar (http://null-byte.wonderhowto.com/how-to/crack-any-master-combination-lock-8-tries-less-using-calculator-0161629/)
Nishant-Wadhwani / Intelligent Infotainment System For Automobiles# Intellifotainment assist” – Smart HMI for passenger cars To run the program, download all files and save them in the same directory. After that, simply run 'Master.py' in the terminal. At the moment, the program will only run in linux based systems. # The Idea Infotainment systems have come a long way since the first set of dashboards installed in cars. Through our idea, we aim to create a Human Machine interaction model that takes infotainment systems to a new level. The driver tends to get distracted from the road while performing secondary tasks such as changing the music track, locking/unlocking the door while driving etc. Our system shall enable the driver to focus only on driving. Controlling the secondary tasks will be much easier. Our product primarily comprises of 5 modules: 1) Attention and drowsiness detection: - A camera shall be present on the dashboard, in front of the driver, behind the steering wheel. Through digital image processing techniques , using hough circle algorithm and haarcascade of an eye, we shall keep track of the driver’s sight. If he or she is looking away from the road while driving for more than a specified amount of time, we shall alert the driver to focus. We shall map the head orientation and iris position to accurately identify the driver’s attention. 2) Infotainment control features using blink combination: Through a combination of blinks, the driver can turn on or of the headlights, tail lights as well as indicators. Blinking of the eyes shall be detected using ‘dlib’ features in python. This shall give extremely accurate results. 3) Voice commands to control wipers, car lock, music system and windows A simple, yet extremely useful idea that would make the life of the driver a whole lot easy. Enabling the driver to speak to his car infotainment system would allow him to control and navigate these functionalities with great ease. The car will be enabled with a virtual assistant. 4) Automatic rear view mirror adjustment scheme: Using the camera placed in front of the driver, the system shall detect the position of the driver’s head. This shall also be done using image processing techniques and we shall identify the coordinates of the driver head in 3D space. There will be a mapping between the head position and mirror adjustment scheme. The mirrors will adjust their position using servo motors and shall do so automatically by identifying the head position. 5) A revolutionary reverse-assistance algorithm for smart parking and general reversing: Probably the highlight of our model, this feature shall make driving the car in and out of a parking spot, or rather, even reversing a car in general, far easier and safer than what it already is. Like most other modern cars, our model shall also have a camera installed at the back and the corresponding image displayed at the infotainment screen for parking assistance. Upon activating the reverse gear, the screen shall trace the line of motion of the car corresponding to the current position of the steering wheel. Because of this feature, the driver gets an idea of whether or not he’ll hit an obstacle while reversing if the steering wheel is kept at that position. Taking this feature to another level, the rear camera, after capturing the live video feed from the back of the car, shall perform image processing and machine learning algorithms to find a safe, obstacle-free path for reversing and indicate the driver to move the steering wheel accordingly. So instead of relying solely on the drivers judgement, our system shall actually find the path to be taken while reversing, such that other cars and other obstacles will be avoided, and accordingly recommend the driver to steer the wheel in that direction. This feature shall be extremely useful for new drivers/ learners. During the initial phase, to prevent errors from creeping in, we will always have a manual override button. After a good amount of testing, further modifications and refinements can be made. Our systems adds new dimensions to both precautionary safety measures, as well as convenience. If implemented properly, we are confident that our project will reach new heights of HMI and driver assistance technology. It will give drivers several less reasons to worry about.
manyasrinivas2021 / AI BASED FACIAL EMOTION DETECTION USING DEEP LEARNING“AI Based Facial Emotion Detection”, developed using many machine learning algorithms including convolution neural networks (CNN) for a facial expression recognition task. The goal is to classify each facial image into one of the seven facial emotion categories considered in this study.Trained CNN models with different depth using gray-scale images from the Kaggle website.CNN models are developed in Pytorch and exploited Graphics Processing Unit (GPU) computation in order to expedite the training process. In addition to the networks performing based on raw pixel data,Hybrid feature strategy is employed by which trained a novel CNN model with the combination of raw pixel data and Histogram of Oriented Gradients (HOG) features. To reduce the over fitting of the models,different techniques are utilized including dropout and batch normalization in addition to L2 regularization. Cross validation is applied to determine the optimal hyper-parameters and evaluated the performance of the developed models by looking at their training histories. Visualization of different layers of a network is presented to show what features of a face can be learned by CNN models. Based on the emotion the program recommends the music for the user to up flit the mood.
sanusanth / C Basic Simple ProgramWhat is C++? C++ is a general-purpose, object-oriented programming language. It was created by Bjarne Stroustrup at Bell Labs circa 1980. C++ is very similar to C (invented by Dennis Ritchie in the early 1970s). C++ is so compatible with C that it will probably compile over 99% of C programs without changing a line of source code. Though C++ is a lot of well-structured and safer language than C as it OOPs based. Some computer languages are written for a specific purpose. Like, Java was initially devised to control toasters and some other electronics. C was developed for programming OS. Pascal was conceptualized to teach proper programming techniques. But C++ is a general-purpose language. It well deserves the widely acknowledged nickname "Swiss Pocket Knife of Languages." C++ is a cross-platform language that can be used to create high-performance applications. C++ was developed by Bjarne Stroustrup, as an extension to the C language. C++ gives programmers a high level of control over system resources and memory. The language was updated 3 major times in 2011, 2014, and 2017 to C++11, C++14, and C++17. About C++ Programming Multi-paradigm Language - C++ supports at least seven different styles of programming. Developers can choose any of the styles. General Purpose Language - You can use C++ to develop games, desktop apps, operating systems, and so on. Speed - Like C programming, the performance of optimized C++ code is exceptional. Object-oriented - C++ allows you to divide complex problems into smaller sets by using objects. Why Learn C++? C++ is used to develop games, desktop apps, operating systems, browsers, and so on because of its performance. After learning C++, it will be much easier to learn other programming languages like Java, Python, etc. C++ helps you to understand the internal architecture of a computer, how computer stores and retrieves information. How to learn C++? C++ tutorial from Programiz - We provide step by step C++ tutorials, examples, and references. Get started with C++. Official C++ documentation - Might be hard to follow and understand for beginners. Visit official C++ documentation. Write a lot of C++ programming code- The only way you can learn programming is by writing a lot of code. Read C++ code- Join Github's open-source projects and read other people's code. C++ best programming language? The answer depends on perspective and requirements. Some tasks can be done in C++, though not very quickly. For example, designing GUI screens for applications. Other languages like Visual Basic, Python have GUI design elements built into them. Therefore, they are better suited for GUI type of task. Some of the scripting languages that provide extra programmability to applications. Such as MS Word and even photoshop tend to be variants of Basic, not C++. C++ is still used widely, and the most famous software have their backbone in C++. This tutorial will help you learn C++ basic and the advanced concepts. Who uses C++? Some of today's most visible used systems have their critical parts written in C++. Examples are Amadeus (airline ticketing) Bloomberg (financial formation), Amazon (Web commerce), Google (Web search) Facebook (social media) Many programming languages depend on C++'s performance and reliability in their implementation. Examples include: Java Virtual Machines JavaScript interpreters (e.g., Google's V8) Browsers (e.g., Internet Explorer, Mozilla's Firefox, Apple's Safari, and Google's Chrome) Application and Web frameworks (e.g., Microsoft's .NET Web services framework). Applications that involve local and wide area networks, user interaction, numeric, graphics, and database access highly depend on C++ language. Why Use C++ C++ is one of the world's most popular programming languages. C++ can be found in today's operating systems, Graphical User Interfaces, and embedded systems. C++ is an object-oriented programming language which gives a clear structure to programs and allows code to be reused, lowering development costs. C++ is portable and can be used to develop applications that can be adapted to multiple platforms. C++ is fun and easy to learn! As C++ is close to C# and Java, it makes it easy for programmers to switch to C++ or vice versa Definition - What does C++ Programming Language mean? C++ is an object oriented computer language created by notable computer scientist Bjorne Stroustrop as part of the evolution of the C family of languages. Some call C++ “C with classes” because it introduces object oriented programming principles, including the use of defined classes, to the C programming language framework. C++ is pronounced "see-plus-plus." C++ Variables Variables are the backbone of any programming language. A variable is merely a way to store some information for later use. We can retrieve this value or data by referring to a "word" that will describe this information. Once declared and defined they may be used many times within the scope in which they were declared. C++ Control Structures When a program runs, the code is read by the compiler line by line (from top to bottom, and for the most part left to right). This is known as "code flow." When the code is being read from top to bottom, it may encounter a point where it needs to make a decision. Based on the decision, the program may jump to a different part of the code. It may even make the compiler re-run a specific piece again, or just skip a bunch of code. You could think of this process like if you were to choose from different courses from Guru99. You decide, click a link and skip a few pages. In the same way, a computer program has a set of strict rules to decide the flow of program execution. C++ Syntax The syntax is a layout of words, expression, and symbols. Well, it's because an email address has its well-defined syntax. You need some combination of letters, numbers, potentially with underscores (_) or periods (.) in between, followed by an at the rate (@) symbol, followed by some website domain (company.com). So, syntax in a programming language is much the same. They are some well-defined set of rules that allow you to create some piece of well-functioning software. But, if you don't abide by the rules of a programming language or syntax, you'll get errors. C++ Tools In the real world, a tool is something (usually a physical object) that helps you to get a certain job done promptly. Well, this holds true with the programming world too. A tool in programming is some piece of software which when used with the code allows you to program faster. There are probably tens of thousands, if not millions of different tools across all the programming languages. Most crucial tool, considered by many, is an IDE, an Integrated Development Environment. An IDE is a software which will make your coding life so much easier. IDEs ensure that your files and folders are organized and give you a nice and clean way to view them. Types of C++ Errors Another way to look at C++ in a practical sense is to start enumerating different kinds of errors that occur as the written code makes its way to final execution. First, there are syntax errors where the code is actually written in an illegible way. This can be a misuse of punctuation, or the misspelling of a function command or anything else that compromises the integrity of the syntax as it is written. Another fundamental type of error is a compiler error that simply tells the programmer the compiler was not able to do its work effectively. As a compiler language, C++ relies on the compiler to make the source code into machine readable code and optimize it in various ways. A third type of error happens after the program has been successfully compiled. Runtime errors are not uncommon in C++ executables. What they represent is some lack of designated resource or non-working command in the executable program. In other words, the syntax is right, and the program was compiled successfully, but as the program is doing its work, it encounters a problem, whether that has to do with interdependencies, operating system requirements or anything else in the general environment in which the program is trying to work. Over time, C++ has remained a very useful language not only in computer programming itself, but in teaching new programmers about how object oriented programming works.
cairnsynth / MUSS3640 Vocal SynthThe MUSS3640 Vocal Synthesiser is a standalone application/VST3 plugin developed to allow exploratory synthesis of the singing voice. It implements a combination of formant-wave-function and bandpass synthesis techniques.
obersteiner / SparseSpACEsparseSpACE - the Sparse Grid Spatially Adaptive Combination Environment implements different variants of the spatially adaptive combination technique.
alonsorobots / FilterPhotogrammetryPhotosWhen you shoot photos for photogrammetry, sometimes you take 5k photos. Looking through them individually would be crazy. This script will help you find bad photos automatically using a combination of traditional computer graphics techniques as well as modern AI ones.
averule / Hand Gesture RecognitionDigital image processing helps replace several mundane activities. My project in final year was ‘Application Control using Hand Gesture Recognition From 3-Dimensional Images’. We worked extensively on processing a 3-D image to recognize the encrypted gesture, with the added 3rd dimension for more number of gestures. We started with extensive image segmentation to suppress background, handle dynamic lighting conditions and extract only portion of hand from the 3-D image. A tedious task, we researched many papers on IEEE and books on Image processing, to come-up with a complex code logic involving a combination of three different segmentation techniques involving RGB, YCbCr and HSV models. Further, with mathematical calculations involving use of Eigen values and Eigen vectors were derived based on the co-variance matrix, generated as per captured image, we managed to extract maximum information. A Euclidean distance was calculated to denote the deviation of captured image from each set of pre-captured images for all defined gestures. Hectic code optimization helped save precious execution time. The gesture corresponding to minimal Euclidean distance was the identified gesture. This project acquainted me with MATLAB and I learnt about various image enhancement and image segmentation techniques. I presented a paper at IEEE’s International Conference on Convergence of Technology (I2CT), Pune, published in the journal with ISBN “978-1-4799-3759-2”.