file_utils.py

# -*- coding: utf-8 -*-
"""file_utils.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1XkO8kSWEohn6mXzYzBDaCtoVJnhPOWGO
"""

import os
import numpy as np
import cv2
import imgproc

# https://github.com/lengstrom/fast-style-transfer/blob/master/src/utils.pyから流用
def get_files(img_dir):
    imgs, masks, xmls = list_files(img_dir)
    return imgs, masks, xmls

def list_files(in_path):
    img_files = []
    mask_files = []
    gt_files = []
    for (dirpath, dirnames, filenames) in os.walk(in_path):
        for file in filenames:
            filename, ext = os.path.splitext(file)
            ext = str.lower(ext)
            if ext == '.jpg' or ext == '.jpeg' or ext == '.gif' or ext == '.png' or ext == '.pgm' :
                img_files.append(os.path.join(dirpath, file))
            elif ext == '.bmp':
                mask_files.append(os.path.join(dirpath, file))
            elif ext == '.xml' or ext == '.gt' or ext == '.txt':
                gt_files.append(os.path.join(dirpath, file))
            elif ext == '.zip':
                continue
                
    return img_files, mask_files, gt_files

def saveResult(img_file, img, boxes, dirname='./result/', verticals=None, texts=None):
    """テキスト検出結果を１つずつ保存
    Args:
        img_file(str): 画像ファイル名
        img(array):生画像のコンテキスト
        boxes:(array):結果ファイルの配列
        shape: BB出力[num_detections, 4] / QUAD出力[num_detections, 4]
    Return:
        None
    """
    
    img = np.array(img)
    
    #結果ファイル作成
    filename, file_ext = os.path.splitext(os.path.basename(img_file))
    
    #結果のディレクトリ
    res_file = dirname + "res_" + filename + '.txt'
    res_img_file = dirname + "res_" + filename + '.jpg'
    
    if not os.path.isdir(dirname):
        os.mkdir(dirname)
        
    with open(res_file, 'w') as f:
        for i, box in enumerate(boxes):
            poly = np.array(box).astype(np.int32).reshape((-1))
            strResult = ','.join([str(p) for p in poly]) + '\r\n'
            f.write(strResult)
            
            poly = poly.reshape(-1, 2)
            cv2.polylines(img, [poly.reshape((-1, 1, 2))], True, color=(0, 0, 255), thickness=2)
            ptColor = (0, 255, 255)
            if verticals is not None:
                if verticals[i]:
                    ptColor = (255, 0, 0)
                    
                    if texts is not None:
                        font = cv2.FONT_HERSHEY_COMPLEX
                        font_scale = 0.5
                        cv2.putText(img, "{}".format(texts[i]), (poly[0][0]+1, poly[0][1]+1), font, font_scale, (0,0,0), thickness=1)
                        cv2.putText(img, "{}".format(texts[i]), tuple(poly[0]), font, font_scale, (0, 255, 255), thickness=1)
    cv2.imwrite(res_img_file, img)