Image Classification MCQ solution | TCS Fresco Play

Disclaimer: The primary purpose of providing this solution is to assist and support anyone who are unable to complete these courses due to a technical issue or a lack of expertise. This website's information or data are solely for the purpose of knowledge and education.

Make an effort to understand these solutions and apply them to your Hands-On difficulties. (It is not advisable that copy and paste these solutions).

All Question of the MCQs Present Below for Ease Use Ctrl + F with the question name to find the Question. All the Best!

If you found answer for any of the questions is wrong. Please do mention in the comment section, could be useful for others. Thanks!

_________________________

Image Classification Hands-on Solution

1. The major function of PCA is to decompose a ________________________ into a set of successive orthogonal components

Multivariate dataset

2. Cross validation gives high variance if the testing set and training set are not drawn from the ______________________

Same Population

3. A normalized image has ___________

Mean = 0 and variance = 1

4. SIFT is mainly used for images that are ___________

less simpled and less organised

5. SVD is used in many fields

TRUE

6. For SVM it is good to have ___________

number of dimensions > the number of samples

7. Normalization is the process of converting ___________

pixel values to normal state

8. The main aim of using SIFT for feature extraction is to obtain features that are very sensitive to changes in scale, rotation, image resolution, illumination, etc.

FALSE

9. The scale-invariant feature transform can be used to detect and describe local features in images.

TRUE

10. Each class in CIFAR -10 dataset has _________ images.

6000

Image Classification Hands-on Solution

11. The data used to tune the model is _____________

Validation Set

12. The number of incorrect predictions that the occurrence is negative is False Negative

TRUE

13. ___________________________ is defined as the percentage of correct predictions

Classification Accuracy

14. Naive Bayes algorithm comes under

Deep Learning

15. In the SVD method, a digital image is decomposed into ________ matrices

3

16. The process of changing the pixel intensity values to achieve consistency in dynamic range for images is ___________.

Image normalization

17. The steps involved in building a classification model are -

Initialize---->Train---->Predict---> Evaluate

18. Data Preprocessing is a step the raw data is converted into a form suitable for subsequent analysis

TRUE

19. The main aim of whitening is to reduce data redundancy

TRUE

Image Classification Hands-on Solution

20. The main aim of using SIFT for feature extraction is to obtain features that are very sensitive to changes in scale, rotation, image resolution, illumination, etc.

FALSE

21. SVM is efficient on

Clear Margin Separation

22. Each layer is composed of ___________, where the computation happens

nodes

23. CIFAR-10 image dataset consists of ____________ training data and _____________ testing data

50k 10k

24. PCA and SVD are dimensionality reduction techniques

TRUE

25. Cross Validation is performed on ________________________

Unknown Data

26. ZCA stands for ___________

Zero Phase Component Analysis

27. ________________________ is the number of correct predictions that the occurrence is positive

False Negative x

28. In cross validation, the number of samples used for training the model is _____________

decreased

29. Data Partitioning will help us to know efficiency of model

TRUE

30. Neural network consists of __________ different layers

3

Image Classification Hands-on Solution

31. Scikit Learn is an machine learning python package.

True

32. Allowing training data to be included in testing data will give actual performance results

FALSE

33. CNN is mainly used in

Image Recognition

34. SIFT stands for ________________

Scale Invariant Feature Transform

35. An input image can be converted into structured form through ___________

Image Analysis

36. CNN is a algorithm in which it comes under

Deep Learning

37. Confusion Matrix is not a technique used to evaluate the performance of a classifier

FALSE

38. Conventional classification algorithms on image data

could not give significant accuracy

39. Identify the unstructured data from the following.

Both image and video clip

(getButton) #text=(Image Classification Hands-on Solution) #icon=(link) #color=(#1bc517)

40. The major steps involved in image classification are ___________

Input Image -> Preprocessing -> Feature Extraction -> Classification

41. Noise can be removed using Data Preprocessing

TRUE

42. The data is split into _________ sets

3

(getButton) #text=(Image Classification Hands-on Solution) #icon=(link) #color=(#1bc517)