Color Extraction

Summary

• Introduction
• Parameters
• Examples
• Usage for developers
• Reference
• License

Introduction

Color extraction refers to the process of identifying and extracting the prominent colors from an image. It involves analyzing the pixel values of an image to determine the dominant colors present and their corresponding intensities. Color extraction can be useful in various applications, including image analysis, design, visualization, and data representation.

Parameters

Inputs

• input - (image -.png|.jpg|.jpeg): This is the original image that the user wants to analyze for colors.

Output

• output - (image -.png): This is the result of the color analysis process from the original image. It is an image that has been processed to only include important or distinctive colors extracted from the original image.
• code_color - (text): This is the information about the color codes corresponding to the analyzed colors from the original image. It is represented by HEX codes (e.g., #FF0000 for red).

Examples

input	code_color	output
	#de7715, #ae2d17, #63623a, #362f13, #f7b808
	#244011, #e3ce54, #5c5a3b, #debb0b, #867a69

Usage for developers

Please find below the details to track the information and access the code for processing the model on our platform.

Requirements

python~=3.10
torch~=2.0.0
sklearn
opencv-python
collections
numpy
Pillow

Code based on AIOZ structure

from PIL import Image
from sklearn.cluster import KMeans
from collections import Counter
import numpy as np
import cv2

...
def get_image(pil_image):
    ...

def get_labels(rimg):
    ...

def RGB2HEX(color):
    ...
    
def do_ai_task(
        input: Union[str, Path],
        model_storage_directory: Union[str, Path],
        device: Literal["cpu", "cuda", "gpu"] = "cpu",
        *args, **kwargs) -> Any:
        
        img = get_image(input)
        reshaped_img = img.reshape(img.shape[0]*img.shape[1], img.shape[2])
        labels, clf = get_labels(reshaped_img)
        counts = Counter(labels)
        center_colors = clf.cluster_centers_
        
        # We get ordered colors by iterating through the keys
        ordered_colors = [center_colors[i] for i in counts.keys()]
        hex_colors = [RGB2HEX(ordered_colors[i]) for i in counts.keys()]

        width = 100 
        height = 500  

        image = Image.new('RGB', (width * len(hex_colors), height))

        for i, color in enumerate(hex_colors):
            x_start = i * width
            x_end = (i + 1) * width
            y_start = 0
            y_end = height

            rgb_color = tuple(int(color.lstrip('#')[index:index+2], 16) for index in (0, 2, 4))

            for y in range(y_start, y_end):
                for x in range(x_start, x_end):
                    image.putpixel((x, y), rgb_color)

        image.save('output.png')
        output = open("output.png", "rb")  # io.BufferedReader
    return output, hex_colors

Reference

This repository is based on and inspired by Shamima Hossain's work. We sincerely thank them for sharing the code.

License

We respect and comply with the terms of the author's license cited in the Reference section.