{"id":19980,"date":"2022-11-22T08:49:46","date_gmt":"2022-11-22T13:49:46","guid":{"rendered":"https:\/\/www.crim.ca\/blogue\/identification-de-baleines-bleues-a-laide-de-la-vision-par-ordinateur\/"},"modified":"2026-01-12T17:05:04","modified_gmt":"2026-01-12T22:05:04","slug":"identification-de-baleines-bleues","status":"publish","type":"blogue","link":"https:\/\/www.crim.ca\/en\/blogue\/identification-de-baleines-bleues\/","title":{"rendered":"Identification of blue whales using computer vision"},"content":{"rendered":"

CRIM’s computer vision team is called upon to solve all kinds of image or video analysis problems related to fields as varied as industrial inspection, dermatology, microscopic imaging, 3D imaging, and so on.<\/p>\n

Recently, she has become interested in the problem of automated animal re-identification, which plays a crucial role in understanding ecosystems. This field is increasingly being studied, not least because of the growing use ofcamera<\/em> traps, which capture large volumes of images of wild animals as they pass in front of cameras. These image volumes are too large for researchers to process manually. Research platforms such as wildme.org, an important tool for citizen science among other things, are also in great need of image analysis algorithms to enable their users to feed databases on the evolution of populations of multiple species. <\/p>\n

Context<\/h2>\n

The Mingan Island Research Station (SRIM) has contacted the CRIM team with a proposal to use its blue whale images to automate the photo-identification process. Whale photo-identification is a demanding activity, requiring time and cutting-edge expertise: <\/p>\n

\"\"
Source \u00a9 SRIM\/MICS<\/figcaption><\/figure>\n

 <\/p>\n

The same whale can be seen in one of the following three photos. Can you tell which one it is and thus pass the photo-identification test? \ud83d\ude01<\/p>\n

A)<\/p>\n

\"\"
Source \u00a9 SRIM\/MICS<\/figcaption><\/figure>\n

B)<\/p>\n

\"\"
Source \u00a9 SRIM\/MICS<\/figcaption><\/figure>\n

C)<\/p>\n

\"\"
Source \u00a9 SRIM\/MICS<\/figcaption><\/figure>\n

The photo corresponding to the unknown whale is photo C, taken three years apart from the first photo. The idea is to check that the blotch patterns between the two individuals are the same [1]: <\/p>\n

Naturally, the development of an automatic photo-identification method could greatly assist biologists in the search for photo matches, for example by reducing the list of possible candidates.<\/p>\n

Over the last 40 years, SRIM has accumulated thousands of images of these cetaceans, along with their metadata. Can all this information be used by artificial intelligence techniques, more specifically computer vision techniques, to support researchers in their photo-identification activities? And which methods are the most promising? <\/p>\n

Automated photo-identification: approach and solutions<\/h2>\n

The literature review on the subject has yielded few results: this is a problem that has received very little attention in the scientific literature. One might think that an algorithm developed to photo-identify another species of whale could serve as a starting point; however, the photo-identification process can be very different from one species to another, sometimes it’s the tail that’s distinctive, sometimes it’s the head or the dorsal fin, and so on. <\/p>\n

It’s the stains on the blue whale’s skin that identify it, and the best algorithmic lead lies in a family of techniques that extract and compare local image features.<\/p>\n

Local features are signatures attached to specific points in an image (e.g. belonging to an object) that have invariance properties, i.e. they have approximately the same value even if the appearance of the object in the image changes markedly (different viewpoint, different illumination, etc.).<\/p>\n

The following figure illustrates the idea, where visually similar (locally) points may have been connected by lines because their signatures are similar, even if the object has a different appearance (rotation, inclination, smaller size):<\/p>\n

\"\"
https:\/\/docs.opencv.org\/3.4\/Feature_Homography_Result.jpg<\/figcaption><\/figure>\n

In this context, like the box of cookies above, two images of the same whale will have several points of correspondence, and the more numerous the correspondences, the higher the chances that the images come from the same individual.<\/p>\n

We evaluated several local feature extraction and comparison algorithms on a good-sized dataset (807 different individuals, 3129 images in total). They can be classified into three categories: <\/p>\n