easyOCR evaluation

[boltonn]

This is amazing work! Any plans to include easyOCR in the benchmark?

https://github.com/JaidedAI/EasyOCR

Secondary ask is if you have a prioritized list of other languagesm

[ouyanglinke]

Thank you for your attention. We will gradually add more models to the evaluation leaderboard, and the easyOCR results will be updated in the OCR module.
Currently, we don't have a schedule for expanding to other language data types, as this requires a high level of expertise from annotators. If there is further support for this work, we will update our TODO list accordingly.

[ouyanglinke]

Hi, we evaluate the EasyOCR in Omnidocbench at OCR module. Here is the result:

Model Type	Model	Language			Text background			Text Rotate
		EN	ZH	Mixed	White	Single	Multi	Normal	Rotate90	Rotate270	Horizontal
Expert Vision Models	EasyOCR	0.260	0.398	0.445	0.366	0.287	0.388	0.360	0.970	0.997	0.926
	PaddleOCR	0.071	0.055	0.118	0.060	0.038	0.0848	0.060	0.015	0.285	0.021
	Tesseract OCR	0.179	0.553	0.553	0.453	0.463	0.394	0.448	0.369	0.979	0.982
	Surya	0.057	0.123	0.164	0.093	0.186	0.235	0.104	0.634	0.767	0.255
	GOT-OCR	0.041	0.112	0.135	0.092	0.052	0.155	0.091	0.562	0.966	0.097
	Mathpix	0.033	0.240	0.261	0.185	0.121	0.166	0.180	0.038	0.185	0.638
Vision Language Models	Qwen2-VL-72B	0.072	0.274	0.286	0.234	0.155	0.148	0.223	0.273	0.721	0.067
	InternVL2-Llama3-76B	0.074	0.155	0.242	0.113	0.352	0.269	0.132	0.610	0.907	0.595
	GPT4o	0.020	0.224	0.125	0.167	0.140	0.220	0.168	0.115	0.718	0.132

This is our model inference code for EasyOCR, aligned with model inference code for other model, adding a 50-pixel white border to each image.

import cv2
import numpy as np
from pathlib import Path
import pdb
import sys
from tqdm import tqdm
import logging

import os
import json
import numpy

from PIL import Image, ImageOps
import easyocr
import pdb

def model_infer(engine, img, lan, img_name):
    img_add_border = add_white_border(img)
    img_ndarray = numpy.array(img_add_border)
    # img = cv2.imdecode(img_ndarray, cv2.IMREAD_COLOR)
    tmp_img_path = f'tmp_easyocr.jpg'
    cv2.imwrite(tmp_img_path, img_ndarray)
    result = engine.readtext(tmp_img_path)

    text = ''
    for idx in range(len(result)):
        res = result[idx]
        t = res[1]
        text += t
    return text

def add_white_border(img: Image):
    border_width = 50
    border_color = (255, 255, 255) 
    img_with_border = ImageOps.expand(img, border=border_width, fill=border_color)
    return img_with_border


def poly2bbox(poly):
    L = poly[0]
    U = poly[1]
    R = poly[2]
    D = poly[5]
    L, R = min(L, R), max(L, R)
    U, D = min(U, D), max(U, D)
    bbox = [L, U, R, D]
    return bbox

def main():
    engine = easyocr.Reader(['ch_sim','en'])

    with open('./OmniDocBench/OmniDocBench.json', 'r') as f:
        samples = json.load(f)
    for sample in samples:
        img_name = os.path.basename(sample['page_info']['image_path'])
        img_path = os.path.join('./OmniDocBench/images', img_name)
        img = Image.open(img_path)
        if not os.path.exists(img_path):
            print('No exist: ', img_name)
            continue
        for i, anno in enumerate(sample['layout_dets']):
            if not anno.get('text'):
                continue
            # print(anno)
            lan = anno['attribute'].get('text_language', 'mixed')
            bbox = poly2bbox(anno['poly'])
            image = img.crop(bbox).convert('RGB') # crop text block
            outputs = model_infer(engine, image, lan, img_name)

            anno['pred'] = outputs
        with open('./OmniDocBench/result/OmniDocBench_easyocr_text_ocr.jsonl', 'a', encoding='utf-8') as f:
            json.dump(sample, f, ensure_ascii=False)
            f.write('\n')

def save_json():
    with open('./OmniDocBench/result/OmniDocBench_easyocr_text_ocr.jsonl', 'r') as f:
        lines = f.readlines()
    samples = [json.loads(line) for line in lines]
    with open('./OmniDocBench/result/OmniDocBench_easyocr_text_ocr.json', 'w', encoding='utf-8') as f:
        json.dump(samples, f, indent=4, ensure_ascii=False)

if __name__ == '__main__':
    main()
    save_json()

Please let us know if there are any issues in the infer code.
If you have no questions about the results, we will update the EasyOCR model results on the evaluation leaderboard soon.