Added README and MTurk html

Author: stevefielding

README.md

@@ -0,0 +1,50 @@
+Automatic Number (License) Plate Recognition
+============================================
+
+##### mturk.html:
+Defines the web interface that will be used by the MTurk workers to label the images.
+Modified from [original](https://github.com/kyamagu/bbox-annotator)
+Use this html/js code with Amazon mechanical Turk. Instructions [here](https://blog.mturk.com/tutorial-annotating-images-with-bounding-boxes-using-amazon-mechanical-turk-42ab71e5068a)
+
+##### genImageListForAWS.py
+Use this module to generate a csv file that can be uploaded to MTurk. You will need the csv file when you
+publish a batch of images for processing
+
+##### inspectHITs.py:
+Once the batch has been completed by the workers you will need to download the results in csv file format,
+and approve or reject each HIT. This application will read the HIT results and overlay the bounding boxes
+and labels onto the images. A text box is provided for accepting or rejecting each HIT. Once complete, your
+accept/reject response will be added to the downloaded csv file, and the new csv file can be uploaded to MTurk
+ 
+##### csvToPascalXml.py:
+Reads the csv file generated by inspectHITs.py, and generates PASCAL VOC style xml annotation files. 
+One xml file for each image.
+
+##### build_anpr_records.py:
+Reads a group of PASCAL VOC style xml annotation files, and combines with associated images to build a 
+TFrecord dataset. Requires a predefined label map file that maps labels to integers
+
+##### Train the object_detection model
+Now you can use tensorflow/models/research/object_detection to train the model
+It goes something like this. Assuming python virtualenv called tensorflow, 
+a single GPU for training and CPU for eval:
+
+cd tensorflow/models/research/object_detection
+
+###### Training
+workon tensoflow  
+python train.py --logtostderr --pipeline_config_path ../anpr/experiment_faster_rcnn/training/faster_rcnn_anpr.config --train_dir ../anpr/experiment_faster_rcnn/training  
+
+###### Eval
+If you are running the eval on CPU, then limit the number of images to evaluate by modifing your config file:  
+130 eval_config: {  
+131 num_examples: 5  
+
+New terminal  
+workon tensoflow  
+export CUDA_VISIBLE_DEVICES=""  
+python eval.py --logtostderr --checkpoint_dir ../anpr/experiment_faster_rcnn/training --pipeline_config_path ../anpr/experiment_faster_rcnn/training/faster_rcnn_anpr.config --eval_dir ../anpr/experiment_faster_rcnn/evaluation  
+
+cd tensorflow/models/research  
+workon tensoflow  
+tensorboard --logdir anpr/experiment_faster_rcnn  

genImageListForAWS.py

@@ -1,4 +1,5 @@
-
+# usage
+# python genImageListForAWS.py --image_dir SJ7STAR_images/2018_03_02 --output_file image_catalog.csv
 from imutils import paths
 import argparse
 import os