CV 2

to extract information from image ( or video ) We need all the following except :

Which of one these are Uses Of Computer Vision ……………….

Using Computer vision we can ……..

Which one of the following does not constitute a fundamental task in the field of computer vision?

………….. Is the process of finding instances of objects in images.

Assists in categorizing the contents present within an image.

is the task of taking an input image and outputting a class or probability of classes that best describes the image

The object of interest may blend into their environment making them hard to identify

.......... Process we remove noise and Sharpen Images

The goal is to recognize objects and provide useful information on it

Is the algorithm needs to know the position of a user and the position of all the objects around as the user moves every thing is updated smoothly

Cv is the same process of computer graphics

Object recognition Can be Approached through Machine learning or Deep learning

Deep Learning offers High accuracy but we need a few amount of data

Machine learning needs a powerful GPU and a lots of labeled training Images

We use supervised learning if we have known data for the output “Trying to predict”

image processing works as a post processing step in Computer vision

What is the critical step in most recognition applications?

Saying that the color histogram is centered at the left region means that …….

What is the goal of feature selection and reduction in image recognition?

Which type of features should be included in a feature vector for image recognition?

Why is feature extraction preferred before training in image recognition?

Which of the following features are typically considered as global features in image recognition?

What is the primary focus of local features in image recognition?

The number of inputs across the entire dataset is equal to the product of the number of samples and the number of input variables.

Global features are focused on a specific something within the image such as the edges.

Features extracted from images can only be categorized globally, not locally.

Feature extraction eliminates the need for selecting the most representative set of features.

Preprocessing is a step that maximizes the probability of successful recognition.

Which of the following statistical measures can be extracted from the Gray-Level Co-Occurrence Matrix (GLCM)?

In GLCM, if the distance between two intensity levels is increased, how does it affect the co-occurrence count?

Which of the following is NOT a step in calculating the GLCM?

How can the size of the GLCM matrix be reduced to decrease the length of the feature vector?

Which of the following statements about Histogram of Oriented Gradients (HOG) is true?

GLCM is an effective method for analyzing color histograms in images.

GLCM is a spatial-based method that considers the arrangement of pixels in an image.

GLCM is an efficient technique for edge detection in computer vision.

GLCM normalization ensures that all elements in the matrix are scaled between 0 and 255.

HOG is a feature descriptor that quantifies the frequency of intensity levels in an image.

How does information flow in a feed-forward neural network?

What is the purpose of the activation function in a neural network?

What is the purpose of backpropagation in training a neural network?

Which type of neural network is known for considering the distance of a point with respect to the center?

Which neural network type is best suited for problems with sequential data, such as time series?

The primary goal of training a neural network is to maximize the cost value until the model's accuracy is satisfactory

Feedforward Neural Network (FNN) is characterized by the absence of loops in the network.

Object recognition in images is a problem that neural networks excel at due to their ability to handle highly complex patterns.

The purpose of the hidden layers in a neural network is to directly produce the final output.

The local minimum problem in neural networks refers to the challenge of finding the smallest possible input values during training.

What are the three pillars essential for a successful ML application?

Why are representative features considered critical in building an accurate computer vision (CV) application?

Why is it advised not to use more features than needed in a machine learning model?

What is the primary purpose of feature selection and reduction techniques?

One of the ways to reduce the number of input features is

Increasing the dataset complexity Trying to find ways to reduce the number of input features emphasizes the goal of decreasing model complexity and associated parameters.

Histograms make it more challenging to visualize intensity values compared to directly looking at the image.

Feature selection aims to find all possible relevant features.

Feature reduction is a useful strategy for simplifying models and avoiding overfitting in machine learning applications.

Feature selection minimizes complexity by identifying the minimum set for accurate ML models