Text detection in images in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load an image using OpenCV.

Computer Vision

import cv2
image = cv2.imread([1])

Drag options to blanks, or click blank then click option'

Aimage.jpg

B'image.jpg'

Ccv2.imread

Dload_image

Attempts:

3 left

💡 Hint

Common Mistakes

Forgetting to put quotes around the filename.

Passing a variable name instead of a string.

The cv2.imread function requires the image file path as a string, so it must be enclosed in quotes.

2fill in blank

medium

Complete the code to convert the image to grayscale.

Computer Vision

gray_image = cv2.cvtColor(image, [1])

Drag options to blanks, or click blank then click option'

Acv2.COLOR_BGR2GRAY

Bcv2.COLOR_GRAY2BGR

Ccv2.COLOR_BGR2RGB

Dcv2.COLOR_RGB2GRAY

Attempts:

3 left

💡 Hint

Common Mistakes

Using RGB instead of BGR conversion codes.

Using grayscale to BGR conversion instead of BGR to grayscale.

To convert a color image to grayscale, use cv2.COLOR_BGR2GRAY because OpenCV loads images in BGR format.

3fill in blank

hard

Fix the error in the code to detect text regions using OpenCV's EAST text detector.

Computer Vision

net = cv2.dnn.readNet([1])

Drag options to blanks, or click blank then click option'

A'frozen_text_detection.pb'

Bfrozen_east_text_detection.pb

C'text_detector.pbtxt'

D'frozen_east_text_detection.pb'

Attempts:

3 left

💡 Hint

Common Mistakes

Omitting quotes around the filename.

Using incorrect model file names.

The model file path must be a string with quotes. The correct file name for EAST text detector is frozen_east_text_detection.pb.

4fill in blank

hard

Fill both blanks to prepare the image blob for the EAST detector.

Computer Vision

blob = cv2.dnn.blobFromImage(image, [1], (320, 320), [2], True, False)

Drag options to blanks, or click blank then click option'

A1.0

B(320, 320)

C(123.68, 116.78, 103.94)

DFalse

Attempts:

3 left

💡 Hint

Common Mistakes

Using the wrong scale factor.

Not subtracting the correct mean values.

The scale factor should be 1.0, and the mean subtraction values are (123.68, 116.78, 103.94) for the EAST model preprocessing.

5fill in blank

hard

Fill all three blanks to extract scores and geometry from the network output.

Computer Vision

scores = output[0, 0, :, :, [1]]
geometry = output[0, 0, :, :, [2]:6]
conf_threshold = [3]

Drag options to blanks, or click blank then click option'

A0

B1

C0.5

D2

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up scores and geometry indices.

Using too high or too low confidence threshold.

The scores are at index 0, geometry at indices 1:6, and a common confidence threshold is 0.5 to filter weak detections.