Class 12 AI (843): Making Machines See MCQs with Answers
Don’t leave your board exam prep to chance!
These Making Machines See MCQs are built exactly as per the latest CBSE syllabus and board exam pattern of class 12 AI. Every question matters — covering all key concepts, question types, and high-scoring topics from this chapter. Practice these thoroughly, and you’ll revise the entire chapter, strengthen your fundamentals, and walk into your exam ready to tackle any question from this topic with confidence.
Q1. Computer Vision is a branch of:
a) Cyber Security
b) Artificial Intelligence
c) Cloud Computing
d) Networking
Q2. Computer Vision enables machines to:
a) Hear sounds
b) Store files
c) See and interpret visual data
d) Translate languages
Q3. Computer Vision is also known as:
a) Smart Vision
b) Machine Vision
c) Digital Vision
d) Auto Vision
Q4. Computer Vision derives meaningful information mainly from:
a) Audio files
b) Digital images and videos
c) Text documents
d) Emails
Q5. Which technology helps Computer Vision systems understand the visual world?
a) Keyboard and Mouse
b) Deep Learning Models
c) Spreadsheet Software
d) Printers
Q6. Which of the following is NOT a Computer Vision application?
a) Facial Recognition
b) Healthcare
c) Optical Character Recognition
d) Email Encryption
Q7. Digital images are stored in a computer as:
a) Paragraphs
b) Sequence of numbers
c) Audio signals
d) Text files
Q8. The smallest unit of a digital image is called:
a) Cell
b) Pixel
c) Dot
d) Grid
Q9. Pixel stands for:
a) Picture Example
b) Picture Element
c) Photo Entry
d) Pixel Element
Q10. Higher image resolution means:
a) Fewer pixels
b) Less detail
c) More detail
d) Smaller file size only
Q11. In a monochrome image, the pixel value representing black is:
a) 255
b) 128
c) 0
d) 1
Q12. In a monochrome image, the pixel value representing white is:
a) 0
b) 64
c) 128
d) 255
Q13. RGB stands for:
a) Red, Gray, Blue
b) Red, Green, Blue
c) Right, Green, Blue
d) Red, Gold, Black
Q14. Each RGB colour channel has values ranging from:
a) 0–100
b) 0–128
c) 0–255
d) 1–256
Q15. Approximately how many colours can be represented using RGB?
a) 256
b) 65,536
c) More than 16 million
d) 1 million
Q16. One byte is equal to:
a) 4 bits
b) 8 bits
c) 16 bits
d) 32 bits
Q17. Binary value 11111111 is equal to:
a) 128
b) 255
c) 256
d) 254
Q18. Which is the first stage of the Computer Vision process?
a) Feature Extraction
b) Image Acquisition
c) Detection and Segmentation
d) High-Level Processing
Q19. Image acquisition refers to:
a) Editing photographs
b) Capturing digital images or videos
c) Compressing images
d) Removing noise
Q20. Which of the following affects image acquisition quality?
a) Lighting conditions
b) Camera resolution
c) Capture angle
d) All of these
Q21. MRI and CT scans are examples of:
a) Database systems
b) Programming languages
c) Specialized imaging techniques
d) OCR tools
Q22. Which is the second stage of the Computer Vision process?
a) Feature Extraction
b) Detection
c) Preprocessing
d) High-Level Processing
Q23. The main purpose of preprocessing is to:
a) Delete images
b) Improve image quality before analysis
c) Store images permanently
d) Increase file size
Q24. Which preprocessing technique removes unwanted distortions and blurriness?
a) Noise Reduction
b) Histogram Equalization
c) Segmentation
d) Object Detection
Q25. Standardizing pixel values to a fixed range (such as 0–1) is called:
a) Histogram Equalization
b) Image Normalization
c) Feature Extraction
d) Cropping
Q26. Which preprocessing technique ensures all images have the same dimensions?
a) Edge Detection
b) Resizing
c) Segmentation
d) Classification
Q27. Histogram Equalization mainly improves:
a) Audio quality
b) Brightness and contrast
c) Internet speed
d) Storage capacity
Q28. Which of the following is NOT a preprocessing technique?
a) Noise Reduction
b) Image Normalization
c) Object Detection
d) Resizing
Q29. Which is the third stage of the Computer Vision process?
a) Feature Extraction
b) Image Acquisition
c) High-Level Processing
d) Segmentation
Q30. Feature Extraction is the process of:
a) Compressing images
b) Identifying important visual patterns
c) Printing images
d) Renaming image files
Q31. Which feature extraction technique identifies boundaries between regions?
a) Corner Detection
b) Texture Analysis
c) Edge Detection
d) Histogram Equalization
Q32. Texture Analysis helps identify:
a) File size
b) Smoothness, roughness and repetitive patterns
c) Image brightness
d) Storage location
Q33. In deep learning, feature extraction is automatically performed by:
a) OCR
b) CNN
c) K-Means
d) GPS
Q34. CNN stands for:
a) Central Neural Network
b) Computer Neural Node
c) Convolutional Neural Network
d) Convolution Node Network
Q35. Which feature extraction technique is based on colour distribution?
a) Corner Detection
b) Edge Detection
c) Colour-based Feature Extraction
d) Histogram Equalization
Q36. Which is the fourth stage of the Computer Vision process?
a) Image Acquisition
b) Detection and Segmentation
c) Feature Extraction
d) High-Level Processing
Q37. Detection and Segmentation are mainly concerned with:
a) Increasing image size
b) Identifying objects or regions of interest
c) Compressing images
d) Storing image files
Q38. Detection and Segmentation are categorized into:
a) Two primary tasks
b) Three primary tasks
c) Four primary tasks
d) Five primary tasks
Q39. Which of the following is a Single Object Task?
a) Object Detection
b) Image Segmentation
c) Classification
d) Semantic Segmentation
Q40. Classification determines:
a) Camera resolution
b) The category of a single object
c) Image brightness
d) File size
Q41. Which algorithm is mentioned for supervised classification?
a) YOLO
b) SSD
c) K-Means Clustering
d) KNN
Q42. Which algorithm is mentioned for unsupervised classification?
a) KNN
b) CNN
c) K-Means Clustering
d) YOLO
Q43. Classification + Localization performs:
a) Only object classification
b) Only object detection
c) Classification along with predicting bounding boxes
d) Image segmentation
Q44. Multiple Object Tasks mainly deal with:
a) One object only
b) Multiple objects in an image
c) Image resizing
d) Image enhancement
Q45. Object Detection identifies:
a) Only image colours
b) Multiple objects and their locations
c) Image brightness
d) Noise in an image
Q46. Which of the following is an Object Detection algorithm?
a) YOLO
b) R-CNN
c) SSD
d) All of these
Q47. Objects in Object Detection are enclosed using:
a) Histograms
b) Bounding Boxes
c) Pixels
d) Layers
Q48. What is the major difference between Classification and Object Detection?
a) Detection identifies and locates multiple objects.
b) Classification is faster.
c) Detection works only on grayscale images.
d) Classification uses bounding boxes.
Q49. Image Segmentation creates:
a) Audio signals
b) Pixel-wise masks for objects
c) Database tables
d) Program code
Q50. Semantic Segmentation:
a) Differentiates every object of the same class
b) Classifies pixels belonging to the same class
c) Detects image noise
d) Predicts image size
Q51. Instance Segmentation:
a) Groups all objects into one class
b) Differentiates individual objects of the same class
c) Removes unwanted pixels
d) Converts images into grayscale
Q52. Which is the final stage of the Computer Vision process?
a) Detection
b) Preprocessing
c) High-Level Processing
d) Feature Extraction
Q53. High-Level Processing mainly focuses on:
a) Capturing images
b) Interpreting recognized objects and scenes
c) Resizing images
d) Removing noise
Q54. Which of the following is performed during High-Level Processing?
a) Object Recognition
b) Scene Understanding
c) Context Analysis
d) All of these
Q55. OCR stands for:
a) Online Character Recognition
b) Optical Character Recognition
c) Optical Colour Recognition
d) Object Character Reading
Q56. OCR is mainly used to:
a) Increase image brightness
b) Extract printed or handwritten text from images
c) Detect fingerprints
d) Resize images
Q57. Which Computer Vision application helps detect manufacturing defects?
a) Surveillance
b) Machine Inspection
c) OCR
d) Biometrics
Q58. Building 3D computer models has applications in:
a) Robotics
b) AR/VR
c) Autonomous Driving
d) All of these
Q59. Fingerprint Recognition is an example of:
a) Encryption
b) Biometrics
c) Compression
d) Segmentation
Q60. Which of the following is a challenge of Computer Vision?
a) Privacy and Security Concerns
b) Difficulty in Image Acquisition
c) Duplicate and False Content
d) All of these
Q61. Which factor makes image acquisition difficult?
a) Lighting variations
b) Different perspectives
c) Occlusions
d) All of these
Q62. OpenCV stands for:
a) Open Computer Vision
b) Open-Source Computer Vision Library
c) Online Computer Vision
d) Open Coding Vision
Q63. Which command is used to install OpenCV in Python?
a) pip install cv2
b) install opencv
c) pip install opencv-python
d) python install opencv
Q64. Which OpenCV function is used to load an image?
a) cv2.imread()
b) cv2.imshow()
c) cv2.resize()
d) cv2.waitKey()
Q65. Which OpenCV function is used to display an image?
a) cv2.imread()
b) cv2.imshow()
c) cv2.imwrite()
d) cv2.resize()
Q66. Which OpenCV function waits for a key press?
a) cv2.destroyAllWindows()
b) cv2.waitKey()
c) cv2.imread()
d) cv2.cvtColor()
Q67. Which OpenCV function converts a colour image into grayscale?
a) cv2.imread()
b) cv2.resize()
c) cv2.cvtColor()
d) cv2.imshow()
Q68. Which platform is used in the chapter to build an image classification model?
a) Scratch
b) TensorFlow Playground
c) Teachable Machine
d) GitHub
Q69. After adding image classes in Teachable Machine, the next step is to:
a) Delete the images
b) Train the model
c) Export the website
d) Resize the images
Q70. The overall purpose of Computer Vision is to:
a) Replace programming languages
b) Enable machines to understand visual information and make intelligent decisions
c) Increase internet speed
d) Create websites only
