Object Recognition and Segmentation

Apply object detection and recognition on the selected image

Overview

Apply object detector You Only Look At CoefficienTs (YOLACT) on the image to detect and recognize objects with segmentation from (Object Recognition App)

Architecture

The application built based on the following nodes:

Image input node

Drag the image you want from your computer

Image To Array node

Convert image to array

Object Detector

Apply object recognition and segmentation using a YOLACT pretrained model (yolact_resnet50_54_800000.pth) on COCO dataset which has 80 categories (classes).

From the segment_image_by input field you can select what object you are looking to find in the image from the dropdown list (Support multi selection). If you select (all) as object_filter, then the algorithm detects all objects in the image.

COCO Categories:

person, bicycle, car, motorcycle, airplane, bus, train, truck, boat, traffic light, fire hydrant, stop sign, parking meter, bench, bird, cat, dog, horse, sheep, cow, elephant, bear, zebra, giraffe, backpack, umbrella, handbag, tie, suitcase, frisbee, skis, snowboard, sports ball, kite, baseball bat, baseball glove, skateboard, surfboard, tennis racket, bottle, wine glass, cup, fork, knife, spoon, bowl, banana, apple, sandwich, orange, broccoli, carrot, hot dog, pizza, donut, cake, chair, couch, potted plant, bed, dining table, toilet, tv, laptop, mouse, remote, keyboard, cell phone, microwave, oven, toaster, sink, refrigerator, book, clock, vase, scissors, teddy bear, hair drier, toothbrush

Image Preview

Preview the input image as output

Sample Run - APP Editor

  • Drag an image from your computer into the image input

  • Select the object_filter from the object detector node

  • Click on execute app

  • Click on the Image Preview node on the output tab to see the result:

  • If you set the object_filter: all, output image:

  • If you set the object_filter: person and dog, output image:

Sample Run - Form

If you want to run any application without going into the app details, Baseet.ai offers this option via Run an Example form in the overview section in the app details page.

For this app, the required inputs are:

  • Select the objects to detect and segment them in the image.

  • Browse for an image from your computer

Click on Run Example. After the app runs successfully, the output section will be shown as follows:

If the selected objects appear in the image, they will be detected. To enlarge the image click on the image.