Spectre Computer Vision

The Initial Apple Size Detector Is Built

By July 16, 2019 No Comments
Reading Time: 2 minutes

Yes, we made it! We built the very first apple-size-detector using a pre-trained model (involving the COCO dataset), that already knew how to recognize simple objects.  

How did we achieve this?

We used the pre-trained model to detect individual apples and draw masks and bounding boxes around them (see output images below). The geometric information of the masks and bounding boxes can now be translated into real-world dimensions such as millimeters and inches.

The first output screen of the apple detector

Initial apple detector: first output

The second output screen of the apple detector

Initial apple detector: second output

The third output screen of the apple detector

Initial apple detector: third output

The fourth output screen of the apple detector

Initial apple detector: fourth output

The initial results proved highly accurate once the system had been optimised. However, due to the nature of the pre-trained data-set, the apple detector was identifying the entire top layer of apples as an ‘apple’, in addition to individual apples. Additionally, more detections were made for cropped or close up apple images as compared with images taken from far away. So, there is still plenty of room for improvement, but we’re stoked how quickly we got the first usable results. This proves we’re getting closer to bringing computer vision to our growers.

Watch this space, as we will let you know about the latest developments very soon!

Leave a Reply

Bitnami