Search Results for "image analysis algorithm" - Page 3

The CVR-Lib (Computer Vision and Robotics Library) is a C++ object oriented library for computer vision. It provides lots of functionality to solve mathematical problems, many image processing and analysis algorithms, classification tools, and much more.

CVSharp (aka Computer Vision in C#) is a Computer Vision project. Until the present day just one part of the whole project was actually developed. It's called CVSharp Lab, an Image Processing Tool.

TBLTools is a set of GATE processing resources that implements the Fast Transformation Based Learning Algorithm. You can train it to learn rules for NLP tasks such as Named Entity Recognition and Shallow parsing.

DigitalEyes is an OCR (Optical Character Recognizer) developed in C/Caml released under GNU GPL by SuM42, as a sophomore project in EPITA.

A collection of Matlab functions and scripts for computing the saliency map for an image, for determining the extent of a proto-object, and for serially scanning the image with the focus of attention.

This project intends to create an indexing search engine, for knowledge management. The primary object is to apply an information retrieval core. And implement a knowledge data discovery theory such as data mining algorithm, text mining.

musicomp is a program which most important element is an evolutionary algorithm which uses data mining methods as a fitness function to generate monophone melodies.

MultiBoost is a C++ implementation of the multi-class AdaBoost algorithm. AdaBoost is a powerful meta-learning algorithm commonly used in machine learning. The code is well documented and easy to extend, especially for adding new weak learners.

NSvm is a .Net Support Vector Machine library written in .Net. NSvm features the SMO algorithm, a few kernels (including ad hoc algorithms for linear kernels). The objectives of NSvm are simplicity, flexibility and extensibility.

Artificial vision library. Objectives are to make an OCR, fingerprint and face identification as some applications through a general purpose learning and pattern relationships algorithm (Currently performs very basic identification).

An omnifont OCR software for KDE. Due to the fact that each step of the OCR process can be visualized you can get a quick idea of how OCR works and where the problems lie. However the program may be of minor/no use for end users in its current state.

This library implements self-organizing neural networks, also called Kohonen Nets. They can be used for high dimensional data analysis. Example: content based image recognition ( CBIR ).

The TreeQ package is a set of C-language applications that implement a automatic machine learning algorithm based on a tree-structured classifier. This approach is particularly effective for high-dimensional continuous data such as audio and video.

Particle Swarm Optimization toolkit (with GUI) - Allows you to implement PSO algorithm for optimization of engineering/finance/management systems.

A C++ library which finds associations within sets of items, using a fast in-memory algorithm.

Java port and extension of MLC++ 2.0 by Kohavi et al. Currently contains ID3, C4.5, Naive (aka Simple) Bayes, and FSS and CHC (genetic algorithm) wrappers for feature selection. WEKA 3 interfaces are in development.

The open source project to port image analysis MaZda program to Linux and OS X platforms. See: http://www.eletel.p.lodz.pl/programy/mazda/

Weka++ is a collection of machine learning and data mining algorithm implementations ported from Weka (http://www.cs.waikato.ac.nz/ml/weka/) from Java to C++, with enhancements for usability as embedded components.

Gemma 4 12B is Google DeepMind’s unified open-weight multimodal model designed for efficient local reasoning, coding, and multimodal understanding. Unlike other Gemma 4 models that rely on separate encoders, the 12B Unified model uses an encoder-free architecture that projects raw image patches and audio waveforms directly into the language model’s embedding space, reducing multimodal latency and simplifying fine-tuning. It supports text, image, audio, and video inputs with text output, making it useful for transcription, image understanding, video analysis, coding, and agentic workflows. The model has 11.95B parameters, 48 layers, a 256K-token context window, and support for over 140 languages. ...

Devstral Small 2 is a compact agentic language model designed for software engineering workflows, excelling at tool usage, codebase exploration, and multi-file editing. With 24B parameters and FP8 instruct tuning, it delivers strong instruction following while remaining lightweight enough for local and on-device deployment. The model achieves competitive performance on SWE-bench, validating its effectiveness for real-world coding and automation tasks. It introduces vision capabilities,...

Gemma 4 is Google DeepMind’s flagship dense open-weight multimodal model, designed for high-end reasoning, coding, agentic workflows, and multimodal understanding. The model contains approximately 30.7B parameters and supports text and image inputs with text generation output, while also processing video as image-frame sequences. Built as the most capable model in the Gemma 4 family, it combines strong reasoning performance with a large 256K-token context window and configurable thinking modes. Gemma 4 31B supports native function calling, structured outputs, and more than 140 languages, making it suitable for enterprise assistants, coding agents, document analysis, and multilingual applications. ...

Ministral 3 3B Base 2512 is the smallest model in the Ministral 3 family, offering a compact yet capable multimodal architecture suited for lightweight AI applications. It combines a 3.4B-parameter language model with a 0.4B vision encoder, enabling both text and image understanding in a tiny footprint. As the base pretrained model, it is not fine-tuned for instructions or reasoning, making it the ideal foundation for custom post-training, domain adaptation, or specialized downstream tasks....

Ministral 3 3B Reasoning 2512 is the smallest reasoning-capable model in the Ministal-3 family, yet delivers a surprisingly capable multimodal and multilingual base for lightweight AI applications. It pairs a 3.4B-parameter language model with a 0.4B-parameter vision encoder, enabling it to understand both text and image inputs. This reasoning-tuned variant is optimized for tasks like math, coding, and other STEM-related problem solving, making it suitable for applications that require logical reasoning, analysis, or structured thinking. Despite its modest size, the model is designed for edge deployment and can run locally, fitting in ~16 GB of VRAM in BF16 or under 8 GB of RAM/VRAM when quantized. ...

Ministral 3 14B Base 2512 is the largest model in the Ministral 3 line, offering state-of-the-art language and vision capabilities in a dense, base-pretrained form. It combines a 13.5B-parameter language model with a 0.4B-parameter vision encoder, enabling both high-quality text understanding/generation and image-aware tasks. As a “base” model (i.e. not fine-tuned for instruction or reasoning), it provides a flexible foundation ideal for custom fine-tuning or downstream specialization. The...