CPV301

The input of computer vision is an image. So what is the output of computer vision?

• The output is the interpretation of an image.

• The output is a processed image.

• The output is the image that has been recovered with the parts that have been noisy-

• All of the others

It is a type of image segmentation, where we change the pixels of an image to make the image easier to analyze. We convert an image from color or grayscale into a binary image, i.e-, one that is simply black and
white. What is the exact name of this process?

• Thresholding Segmentation.
  

• Edge-Based Segmentation.

• Region-Based Segmentation.

• Watershed Segmentation.

Choose the best description of the Hough transform

• The Hough transform is a technique that can be used to isolate features of a particular shape within an image.

• Hough transform can be employed in applications where a simple analytic description of a feature is not possible.

• The main advantage of the Hough transform technique is that it is tolerant of gaps in feature boundary descriptions and is relatively unaffected by image noise.

• All of the others

Algorithms used for face detection based on what set features to recognize faces? Choose the best correct

answer

• Eyes, eyebrows, nose, hair, jaw

• Eyes, eyebrows, nose, neck, mouth

• Eyes, eyebrows, nose, mouth, jaw

• Eyes, eyebrows, jaw, neck, ear

What is the basic principle of object detection?

• Object detection is based on the features that make up the object.

• Each object's surface has a different structure and shape. Hence object detection relies on color relevance.

• Object detection is based on the semantics of the objects in the image.

• All of the others

Choose the best description of the feature descriptors

• Feature descriptor is an algorithm that takes an image and outputs feature vectors.

• Feature descriptors are used to find the essential features from the given image

• Feature descriptors are used to convert features to other representations through spatial transformations.

• All of the others

After extracled features and their descriptors from two or more images then the next is to establish some preliminary feature matches between these images. Which name is it called?

• Feature reduce

• Feature combination

• Feature compression

• Feature matching

Choose the best answer about digital image

• The digital image is a two-dimensional array of color

• The digital image is a matrix of pixels.

• The digital images are composed of a combination of colors.

• The digital images are created from digital cameras through a mechanical system.

How are thresholding methods implemented? Choose the best answer

• lt replaces each pixel in an image with a black pixel if the image intensity is less than some fixed constant.

• It replaces each pixel in an image with a white pixel if the image intensity is greater than that constant.

• The first and second is correct

• The first or second is correct

In ........, the value of an output pixel is also computed as a weighted sum of neighboring pixels.

• Filter

• Correlation

• Kernel

• Point