Machine learning assistant for image analysis
Systems, methods, and non-transitory computer readable media are provided for labeling depictions of objects within images. An image may be obtained. The image may include a depiction of an object. A user's marking of a set of dots within the image may be received. The set of dots may include one or more dots. The set of dots may be positioned within or near the depiction of the object. The depiction of the object within the image may be labeled based on the set of dots.
1. A system comprising:
one or more processors;
memory storing instructions that, when executed by the one or more processors, cause the system to perform:
obtaining an image, the image including a depiction of an object;
receiving a user's marking of a set of dots within the image, the set of dots including one or more dots and positioned within or near the depiction of the object; and
labeling the depiction of the object within the image based on the set of dots, wherein labeling the depiction of the object within the image based on the set of dots includes identifying a boundary of the object depicted within the image based on position of the set of dots within the image.
2. The system of claim 1 , wherein the position of the set of dots within the image indicates a middle portion of the object.
3. The system of claim 1 , wherein the position of the set of dots within the image indicates a boundary portion of the object.
4. The system of claim 1 , wherein the position of the set of dots within the image indicates a nearby depiction of the object.
5. The system of claim 1 , wherein labeling the depiction of the object within the image is further based on a number of dots within the set of dots.
6. The system of claim 1 , wherein a label of the depiction of the object within the image is used to train a machine learning model for identifying other depictions of the object within other images.
7. The system of claim 6 , wherein identifications of the other depictions of the object within the other images are filtered based on an object size criteria or an object shape criteria.
8. A method implemented by a computing system including one or more processors and storage media storing machine-readable instructions, wherein the method is performed using the one or more processors, the method comprising:
obtaining an image, the image including a depiction of an object;
receiving a user's marking of a set of dots within the image, the set of dots including one or more dots and positioned within or near the depiction of the object; and
labeling the depiction of the object within the image based on the set of dots, wherein labeling the depiction of the object within the image based on the set of dots includes identifying a boundary of the object depicted within the image based on position of the set of dots within the image.
9. The method of claim 8 , wherein the position of the set of dots within the image indicates a middle portion of the object.
10. The method of claim 8 , wherein the position of the set of dots within the image indicates a boundary portion of the object.
11. The method of claim 8 , wherein the position of the set of dots within the image indicates a nearby depiction of the object.
12. The method of claim 8 , wherein labeling the depiction of the object within the image is further based on a number of dots within the set of dots.
13. The method of claim 8 , wherein a label of the depiction of the object within the image is used to train a machine learning model for identifying other depictions of the object within other images.
14. The method of claim 13 , wherein identifications of the other depictions of the object within the other images are filtered based on an object size criteria or an object shape criteria.