Rehan Guha’s Post

🚀 Day 9/30 – Real-Time Image Filters using OpenCV 🐍📷✨ Day 9 of my 30 Days Python Challenge, and today I built a real-time image filter project using OpenCV 🎉 I experimented with different live filters, including: ✨ Original ✨ Grayscale ✨ Edge Detection ✨ Sepia ✨ Blur This hands-on project helped me understand how real-time frame processing and filter pipelines work behind the scenes in computer vision applications 💻 What I focused on today: ✨ Applying multiple filters in real time ✨ Live webcam frame processing with OpenCV ✨ Strengthening image processing fundamentals ✨ Exploring creative computer vision workflows This OpenCV streak is helping me move from basic transformations to visually engaging real-world projects 🚀 👉 Would love your feedback! 👉 Which filter should I add next? 😄 Day 10 coming tomorrow… stay tuned 👀 #Python #OpenCV #ComputerVision #ImageProcessing #30DaysChallenge #PythonProjects #AI #MachineLearning

🚀 Excited to Share My Machine Learning Project! 🐶🐱 Cats vs Dogs Classification using SVM I recently built a Machine Learning model to classify images of cats and dogs using the Support Vector Machine (SVM) algorithm. This project helped me explore image classification and model optimization techniques. 💡 Key Highlights: 🖼️ Image preprocessing and feature extraction 🤖 Classification using Support Vector Machine (SVM) 📊 Model training and evaluation ⚡ Improved accuracy through parameter tuning 🛠️ Tech Stack: Python | Scikit-learn | OpenCV | NumPy | Matplotlib 🔗 Project Link: https://lnkd.in/gz43DmSG This project enhanced my understanding of machine learning algorithms and computer vision basics. Looking forward to building more AI-powered solutions! 💡 #MachineLearning #Python #ComputerVision #SVM #AI #Projects #Learning

Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. Prior to version 1.21.0, the ExternalDataInfo class in ONNX was using Python’s setattr() function to load metadata (like file paths or data lengths) directly from an ONNX model file. It didn’t check if the "keys" in the file were valid. Due to this, an attacker could craft a malicious model that overwrites internal object properties. This issue has been patched in version 1.21.0.

🌸 GAMS is heading to National Harbor for #INFORMS2026 🌸 We’ll be back at the INFORMS Analytics+ Conference (April 12–14) with a hands-on workshop on building and solving optimization models in Python using GAMSPy, including how machine learning components can be embedded directly into those models. 📌 Bridging Optimization and Machine Learning: An Exploration with GAMSPy 📅 Sunday, April 12 | 1:00–2:45 PM 📍 Room: Camellia 1 Join Steve Dirkse and Adam Christensen for a practical walkthrough of GAMSPy, from core modeling concepts (sets, parameters, variables, equations) through to solving models and working with results in Python. The session also explores how structures like neural networks and regression trees can be incorporated into optimization models. Interested? Register here or DM us with any questions: 👉 https://lnkd.in/dSYEXuJ3 #INFORMS2026 #AnalyticsPlus #OperationsResearch #Optimization #GAMSPy #Python #MachineLearning

🚀 Day 8/30 – Image Transformations using OpenCV & Python 🐍📷 Day 8 of my 30 Days Python Challenge, and today I focused on strengthening my Computer Vision fundamentals ✨ I explored some essential image transformation techniques using OpenCV, including: ✨ Resize – changing image dimensions ✨ Crop – extracting a specific region ✨ Flip – horizontal and vertical transformations ✨ Rotate – rotating images at different angles ✨ Translation – shifting images across axes This hands-on practice helped me better understand how images are manipulated behind the scenes in real-world vision applications 💻 Every small concept is helping me build a stronger base for advanced OpenCV and AI projects 🚀 👉 Would love your feedback! 👉 Which image processing concept should I explore next? 😄 Day 9 coming tomorrow… stay tuned 👀 #Python #OpenCV #ComputerVision #ImageProcessing #30DaysChallenge #PythonProjects #AI #MachineLearning

Most AI systems are answering questions about a world that no longer quite exists. David Knickerbocker, founder of Verdant Intelligence and author of Network Science with Python (Packt), on why freshness is a first-class design constraint, not an optimization to add later. Read Deep Engineering Issue #43 → https://lnkd.in/gu2nX4aK #KnowledgeGraphs #GraphRAG #AIEngineering #DeepEngineering #AI

If you're building projects in Computer Vision, knowing the right OpenCV functions can save you a lot of time. Here’s a concise breakdown of essential OpenCV functions used in: • Image processing • Feature extraction • Object detection A quick reference you can revisit anytime. 🔖 Save for later 💬 Open to feedback & suggestions #python #opencv #cheatsheets #coding #Ai #notes

Open-sourcing SynthonOR: a simple synthon similarity search in Python which works on generic RDKit fingerprints , combining them with a binary OR. Demo: https://lnkd.in/dK7uNU87 GitHub: https://lnkd.in/dp_ZGMuw  SynthonOR currently supports multiple fingerprint families, including: ECFP4, ECFP6, RDKit, Topological Torsion, Atom Pair and others will come soon. What makes it interesting to me is not extra complexity, but the opposite: - unlike SynthonGPT, there is no AI and the core idea is super simple - unlike SpaceLight, Hyperspace or FTrees, it does not rely on any chemical heuristics, fragment decompositions, reaction processing, connector-specific tricks, topological representation or hand-crafted assembly logic - it is basically a “pure fingerprints” approach, which makes it a useful and transparent baseline And despite that simplicity, the early benchmark signal is encouraging: on a ChEMBL query slice, including gnarly molecules like peptides or macrocycles, SynthonOR shows a better distribution of Tanimoto similarities than SpaceLight, i.e. it tends to retrieve more fingerprint-similar molecules on this benchmark slice. I like methods that are easy to explain, easy to reproduce, and hard to overfit with hidden heuristics. SynthonOR is my attempt at that for synthon-space retrieval. #Cheminformatics #DrugDiscovery #RDKit #OpenSource #MolecularDesign #VirtualScreening #ComputationalChemistry

The Art of Focus: Mastering Image Cropping with NumPy! 🎯✂️ Day 86/100 In a world of data noise, the ability to focus on what matters is a superpower. For Day 86 of my #100DaysOfCode journey, I explored Region of Interest (ROI) Extraction. In Computer Vision, we don't always need the full picture. By using NumPy Array Slicing, I can 'zoom in' on specific coordinates to isolate faces, text, or objects for further analysis. Technical Highlights: 🎯 ROI Identification: Mastering the coordinate system to pinpoint and extract sub-matrices from large image arrays. ✂️ Precision Slicing: Leveraging Python's [start:stop] syntax to perform lossless cropping in microseconds. ⚡ Computational Optimization: Learning why reducing image size via cropping is the first step in high-speed object detection. 🤖 AI Preprocessing: Understanding how cropping helps prepare datasets for deep learning models by removing irrelevant background noise. Do check my GitHub repository here : https://lnkd.in/d9Yi9ZsC #100DaysOfCode #ComputerVision #NumPy #Python #BTech #IILM #AIML #ImageProcessing #DataScience #SoftwareEngineering #LearningInPublic #WomenInTech