How to reshape numpy image array for color channel

Question

I am working on a captcha recognition project with Keras library. For training set, I am using the following function to generate at most 5 digit captchas.

def genData(n=1000, max_digs=5, width=60):
    capgen = ImageCaptcha()
    data = []
    target = []
    for i in range(n):
        x = np.random.randint(0, 10 ** max_digs)
        img = misc.imread(capgen.generate(str(x)))
        img = np.mean(img, axis=2)[:, :width]
        data.append(img.flatten())
        target.append(x)
    return np.array(data), np.array(target)

Then, I am trying to reshape training data array like following;

train_data = train_data.reshape(train_data.shape[0], 60, 60, 3)

I guess my captchas have 3 color channel. However, when I tried to reshape the training data I am facing with the following error;

ValueError: cannot reshape array of size 3600000 into shape (1000,60,60,3)

Note: If I try with 1 instead of 3. the error is not occurring but my accuracy is not even close to %1

Wilmar van Ommeren · Accepted Answer · 2017-05-11 14:42:27Z

1

You are creating a single channel image by taking the mean. The error says that you are trying to reshape an array with 3600000 elements in an array three times as big (1000*60*60*3 = 10800000). Adapt your function the example below to get it to work.

Also, because you are decreasing the width of your image to 60 pixels the target is not correct anymore. This explains the low accuracy. Try using a bigger width and your accuracy will most likely increase (e.g 150-155).

def genData(n=1000, max_digs=5, width=60):
    capgen = ImageCaptcha()
    data = []
    target = []
    for i in range(n):
        x = np.random.randint(0, 10 ** max_digs)
        img = misc.imread(capgen.generate(str(x)))
        img = img[:,:width,:]
        data.append(img.flatten())
        target.append(x)
    return np.array(data), np.array(target)

edited May 11, 2017 at 14:42

answered May 11, 2017 at 14:22

Wilmar van Ommeren

7,7276 gold badges38 silver badges70 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

cnian Over a year ago

thanks a lot for your suggestions. I didn't realize that taking mean is reducing the depth to 1. I will continue with the same structure but I have one more question. I am creating captchas with different lengths, so the size of the each image is different. Do I need to train my model separately for each length? @Wilmar

Wilmar van Ommeren Over a year ago

No that would take to much time and effort. It would be better to resize the captha's so that they are all the same the same size. But, what you are doing is decreasing the width. It is better to increase the width of the captchas which are too small, by adding zeros or whatever values. Than you won't loose information

Collectives™ on Stack Overflow

How to reshape numpy image array for color channel

1 Answer 1

2 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Related