This project helps detect the around 75 objects of our daily lives.
This project detect object through camera of your laptop or desktop. If you have external camera or web camera you have to change a little in code:
cap = cv2.VideoCapture(0) #1 for External Camera
You can also detect object from ip camera. For that i am working on that code:
For detecting the object from video and picture code will be uploading soon.
The list of object that it can detect are listed below: ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'street sign', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe', 'hat', 'backpack', 'umbrella', 'shoe', 'eye glasses', 'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket', 'bottle', 'plate', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'mirror', 'dining table', 'window', 'desk', 'toilet', 'door', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'blender', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush', 'hair brush']
It has pretty good accuracy. For this we don't have to train any model. It already has opencv model for detection face then it's also have already train neural netwotk model to reconigze for gender.
For Running this project we can open through cmd by calling Run.py or by direct clicking on testing.py will also open in cmd. Or through any text editor biscally it will works fine with idle of python. You can also try with other editor too but i am not sure about whether it will run on other editor or not. But Dont't worry it will work perfectfly on cmd. if any help is needed you can contact me on below address: [email protected]