AI-102 Question 134
Single answerYou are building an AI solution that processes images captured by security cameras. The solution needs to identify specific objects, such as cars and people, and their locations within the image. Which type of model should you use to meet these requirements?
- A
Image classification
- B
Object detection
- C
Semantic segmentation
- D
Optical character recognition (OCR)
Show answer and explanation
Correct answer: B
Explanation
Object detection is the correct choice because it not only identifies specific objects such as cars and people but also provides their locations within the image using bounding boxes, which aligns with the requirements of the solution. Other options either lack location information or are intended for different use cases.
- A. Incorrect.
Image classification assigns a single label to the entire image or determines the presence of categories in the image but does not provide the locations of objects, which makes it unsuitable for this scenario.
- B. Correct.
Object detection identifies specific objects within an image and provides their bounding boxes, making it the ideal model for this requirement.
- C. Incorrect.
Semantic segmentation assigns a label to every pixel in the image to understand the image's structure. While detailed, it is more suited for tasks like scene understanding and not for identifying specific objects with bounding boxes.
- D. Incorrect.
Optical character recognition (OCR) is designed for extracting text from images and is not applicable to identifying objects like cars or people.