Search Results for "visual-" - Page 16

Various datasets from my computer vision research primarily useful for lane detection and visual servoing algorithms.

OSCEAN is an Open Source Content Environment and Abstract Network. It's meant to be an Operating System that runs on top of your current OS as an interface to a universal operating system the user can access at any computer running OSCEAN.

Keyword spotting through speech recognition, linked to media display/playback (visual: photos, video?)

Fuzzy logic add-in for OpenOffice.org Calc. InrecoLAN FuzzyMath allows to perform ordinary arithmetic operations and use ordinary mathematical and financial functions with fuzzy numbers. Have any ideas how to improve this project - you are welcome!

Interface and example projects for CLIPS on NT using the CLIPS DLL. Includes Web/CGI interface.

Structlab is a machine learning C++ framework for structured domains, which provides a toolbox of learning methods and tools for preprocessing and visualization. It also provides a GUI to setup elaborate experiments in a visual and intuitive way.

This project is to share my work in visual recognition of gestures. It shows how I have implemented person detection, color adaptation and tracking of the user's right-hand, gesture feature extraction, etc. using a single videocamera.

SimMetrics is a Similarity Metric Library, e.g. from edit distance's (Levenshtein, Gotoh, Jaro etc) to other metrics, (e.g Soundex, Chapman). Work provided by UK Sheffield University funded by (AKT) an IRC sponsored by EPSRC, grant number GR/N15764/01.

SenseRank Sys: - builds the dictionaries (multidim matrices) of words’ values; - for the set utterance in certain language builds a figure in multidimensional space (in the matrix space) of values (visual schema), which is topological view of sense

RobotFlow is a mobile robotics tookit based on FlowDesigner. The visual programming interface provided with FlowDesigner will help people to better visualize & understand what is really happening in the robot's control loops, sensors and actuators.

mbFuzzIT enables the work with Fuzzy technology (fuzzy inference / fuzzy logic) in Java. In order to facilitate the creation of the inference mechanisms, mbFuzzIT containts a visual editor.

DTW is intended to be a Voice in -> Pictures + Text out program written in java using Sphinx from CMU. This is intended to be useful to people who have good oral/visual literacy skills but poor written literacy skills.

MEM Net - Mote EMulator Network. This project will focus on: 1) MEM - Wireless Sensor Node (mote) emulator 2) MEM Net - network of emulated motes So far, the only released package is “visual-sim-slides”. More comming next !

An attempt at developing an Artificial Inteligence software, based on the notion that inteligence is a set of conditional choices (in programming terms, it means a whole lot of if statements).

Visual CCG is a set of tools to help one view and manipulate XML-based CCG (Complex Categorical Grammars) tools.

Pangaea will be a robust and feature filled game engine built using Allegro (http://alleg.sourceforge.net) It will be similar to Final Fantasy 1-3, etc., complete with map editor/world builder.

This project aims to create a block oriented visual workbench for general purpose systems modelling and simulation. In the first milestone, we`ll build a simple GUI and the basic blocks to model neural network training and internetwork topologies.

Medical decision making algorithm tool. Visual design tool generates Tcl/Tk code. Non-programmers can design interactive algorithms. Generates notes for inclusion in medical record. Runs freestanding or in Tcl Plugin.

A collection of user contributed applications which use the Open Computer Vision Library

Qwen2.5-VL-7B-Instruct is a multimodal vision-language model developed by the Qwen team, designed to handle text, images, and long videos with high precision. Fine-tuned from Qwen2.5-VL, this 7-billion-parameter model can interpret visual content such as charts, documents, and user interfaces, as well as recognize common objects. It supports complex tasks like visual question answering, localization with bounding boxes, and structured output generation from documents. The model is also capable of video understanding with dynamic frame sampling and temporal reasoning, enabling it to analyze and respond to long-form videos. ...

Lastest.cloud is a free, open-source verification of development, self-hosted visual regression and end-to-end testing platform for web applications. An AI agent records you clicking through your running app and generates Playwright tests with multi-selector fallback. Replays are deterministic and token-free, so your CI/CD bill doesn't scale with your test suite. Lastest ships three diff engines side-by-side — pixel (pixelmatch), structural (SSIM), and perceptual (Butteraugli) — so flaky pixel diffs stop crying wolf. ...

...Unlike Krea 2 Turbo, which is distilled and optimized for faster direct generation, Raw is the foundational checkpoint before additional post-training and fine-tuning. This makes it especially useful for developers, researchers, and creative teams who want to customize the model for specific styles, domains, products, or visual workflows. It supports Diffusers, the official Krea codebase, and SGLang, and it can be used to train LoRAs that are later compatible with Krea 2 Turbo. Krea 2 Raw is intended for image generation, concepting, design exploration, visual production, and creative tool integration under the Krea 2 Community License.

...As part of the Qwen2.5 series, it supports image-text-to-text generation with capabilities like chart reading, object localization, and structured data extraction. The model can serve as an intelligent visual agent capable of interacting with digital interfaces and understanding long-form videos by dynamically sampling resolution and frame rate. It uses a SwiGLU and RMSNorm-enhanced ViT architecture and introduces mRoPE updates for robust temporal and spatial understanding. The model supports flexible image input (file path, URL, base64) and outputs structured responses like bounding boxes or JSON, making it highly versatile in commercial and research settings. ...

...It is designed to handle complex end-to-end software workflows across multiple languages and domains, including front-end development, DevOps, performance optimization, and coding-driven design. Beyond coding, it can transform prompts and visual inputs into production-ready interfaces and lightweight full-stack outputs with structured layouts, interactivity, and polished visual detail. One of its most distinctive capabilities is horizontal agent scaling, supporting up to 300 sub-agents and 4,000 coordinated steps in a single run, which enables parallel task decomposition and end-to-end completion of outputs such as documents, websites, and spreadsheets. ...

...The model encourages open-source collaboration, requiring derivative models and LoRAs to be shared under the same terms. Sponsored by Lanyun Cloud, it represents a community-driven effort to democratize advanced, high-quality visual generation.