ML/DL/AI

Image Processing

• Face Recognition using FaceNet and MobileNet

• Object Detection using YOLOv5 and YOLOv8

• Emotion & Gender Classification using WiseResNet

• Pose Detection using OpenPose and MediaPipe

• Hand Gesture Recognition using OpenCV and ConvLSTM

• Image Matching using SIFT and ORB Descriptors

• OCR on Invoices, ID Cards, and Handwritten Documents using Tesseract, OCR.space API, and Google Vision API

• License Plate Detection and OCR using OpenCV and EasyOCR

• Fingerprint Recognition using Gabor Filters and CNN

• Image & Video Content Classification using ResNet50

• Age Estimation using MobileNetV2 and DeepFace

AI Experience with Chatbot / NLP / RAG

• Contextual Chatbot using Retrieval-Augmented Generation (RAG) with OpenAI embeddings + Pinecone vector DB

• Medical FAQ Bot using LangChain, ChromaDB, and PDF ingestion

• Legal Document Q&A using RAG pipeline (Hugging Face Transformers + ElasticSearch)

• Multi-turn Chatbot with GPT-4 + Custom Retrieval API

• Enterprise Chat Assistant using Azure Cognitive Search + OpenAI

• Document Summarization & Topic Extraction using BERT and spaCy

• Custom Search-Augmented Answering using Haystack, FAISS, and Sentence-BERT

Audio Processing

• Speech Recognition using Wav2Vec 2.0, Whisper, and Google Speech-to-Text

• Emotion Detection from Voice using MFCC Features + CNN-LSTM

• Speaker Identification using i-vectors and x-vectors with Kaldi

• Audio Classification (Gunshot, Glass Break, etc.) using YAMNet and VGGish

• Real-time Wake Word Detection using Porcupine and TensorFlow Lite

• Language Identification from Audio using ResNet + Spectrogram Pipeline

• Audio Keyword Spotting using DS-CNN and MFCC Pipeline