madsrossen/fish_box

fish box

Fish box

This repo features an image processing algorithm that undistorts images along with segmentation of cod and classification of damage to cod.

The input is pictures of cod and the output is an image where wound on cod is marked and tagged along with a CDI (catch damage index). The CDI marks which image file names that contains cod with wounds.

How to use

1. Put cod images into fish_pics/input_images.

2. Select the run mode by setting the script parameters in the configurations or passing them in command line/terminal/shell. How to pass arguments for a python script :

   • "n" : Run the program using only openCV functions
   • "y" : Run the program using own built functions
   • "y e": Run the program using own built functions, and see not yet finished version of future implementations

   NOTE: when running the program using own built functions it normally takes 420 sec. for one image. Consider having only few images in fish_pics/input_images

3. The output is saved.

   1. Images for manual inspection is saved in fish_pics/output_images/manual_inspection
   2. Images for manual inspection with CLAHE applied is saved in fish_pics/output_images/manual_inspection_CLAHE
   3. Images where wounds are marked are saved in fish_pics/output_images/marked_images
   4. The CDI is saved in output_CDI

• Optional: run recalibration of intrinsic parameters for undistortion:
  1. Put checkerboard images into calibration/checkerboard_pics
  2. Run the python script calibration/main_harris-corner-detection.py. A .mat file is generated - "calibration/image_points_checkerboard/image_points_for_MATLAB.mat"
  3. Run the MATLAB script calibration/GetCameraParameters.m that uses the .mat file generated from previous step. The script generates the parametres k_1, k_2, imgCenterX, imgCenterY, Fx and Fy, that is py into parameters.yaml. The intrinsic parameters are now calibrated

Reference to algorithms and math used in code

1. Grass fire algorithm
2. Harris corner detection
3. Thresholding
4. Find center of contur mass
5. Camera calibration
6. Blur

---

Morphology

7. Erosion
8. Dialation
9. Opening
10. Closing
11. Sobel operator

---

Color converting

12. Gray scaling
13. RGB to HSV

fish_box's Issues

Skaber fejl når der køres længere x akser som y akser skal fikses

fish_box/harris-corner-detection.py

Line 71 in aa6daca

CornerCoordinate.append([x, y, Ix[x,y], Iy[x,y], r])

Revers row and col

fish_box/sobel_filter.py

Line 7 in 2ea982b

col, row = np.shape(file)

they ar reversed, and so are x and y too.

fish_box/sobel_filter.py

Lines 23 to 29 in 2ea982b

	Iy = np.sum(np.multiply(gy, file[x:x+3, y:y+3])) # multiply two 3x3 matrix together in y
	Ix = np.sum(np.multiply(gx, file[x:x+3, y:y+3])) # multiply two 3x3 matrix together in x
	Iyy[x, y] = Iy
	Ixx[x, y] = Ix
	sobel_image[x, y] = np.sqrt(Ix**2 + Iy**2)