Sunday, January 6, 2019

Real-Time Hand Gesture Recognition (with source code) using Python | Codeing School

Real-Time Hand Gesture Recognition (with source code) using Python | Codeing School
Real-Time Hand Gesture Recognition (with source code) using Python

Hand gesture recognition is exceptionally critical for human-PC cooperation. In this work, we present a novel continuous technique for hand gesture recognition. In our system, the hand locale is removed from the foundation with the foundation subtraction technique. At that point, the palm and fingers are divided in order to identify and perceive the fingers. At last, a standard classifier is connected to foresee the marks of hand gestures. The tests on the informational index of 1300 pictures demonstrate that our technique performs well and is exceedingly proficient. Additionally, our strategy demonstrates preferable execution over a condition of-craftsmanship technique on another informational collection of hand gestures.


As we probably are aware, the vision-based innovation of hand gesture recognition is an essential piece of human-PC communication (HCI). In the most recent decades, console and mouse assume a noteworthy job in human-PC communication. Nonetheless, attributable to the fast improvement of equipment and programming, new sorts of HCI strategies have been required. Specifically, advances, for example, discourse recognition and gesture recognition get extraordinary consideration in the field of HCI.

The gesture is an image of physical conduct or passionate articulation. It incorporates body gesture and hand gesture. It falls into two classifications: static gesture and dynamic gesture. For the previous, the stance of the body or the gesture of the hand signifies a sign. For the last mentioned, the development of the body or the hand passes on a few messages. The gesture can be utilized as a device of correspondence among PC and human. It is enormously not quite the same as the customary equipment based techniques and can achieve human-PC collaboration through gesture recognition. Gesture recognition decides the client purpose through the recognition of the gesture or development of the body or body parts. In the previous decades, numerous specialists have strived to enhance the hand gesture recognition innovation. Hand gesture recognition has an extraordinary incentive in numerous applications, for example, communication via gestures recognition, enlarged reality (computer generated reality), gesture-based communication translators for the handicapped, and robot control.


Web Cam

Source Code:

Run Process:

Put them in the same folder.

1st run It will train your machine, with the help of Capture.png

2nd run, it gives the final output. Put your hand in the green box.



  1. Replies
    1. I am glad that I saw this post. It is informative blog for us and we need this type of blog thanks for share this blog, Keep posting such instructional blogs and I am looking forward for your future posts.
      python projects for students

      Data analytics is the study of dissecting crude data so as to make decisions about that data. Data analytics advances and procedures are generally utilized in business ventures to empower associations to settle on progressively Python Training in Chennai educated business choices. In the present worldwide commercial center, it isn't sufficient to assemble data and do the math; you should realize how to apply that data to genuine situations such that will affect conduct. In the program you will initially gain proficiency with the specialized skills, including R and Python dialects most usually utilized in data analytics programming and usage; Python Training in Chennai at that point center around the commonsense application, in view of genuine business issues in a scope of industry segments, for example, wellbeing, promoting and account.

      Project Center in Chennai

  2. This happens when i run the 1st process
    ValueError: not enough values to unpack (expected 3, got 2)

  3. _, contours, _ = cv2.threshold(hand, 70, 255, cv2.THRESH_BINARY)
    ValueError: not enough values to unpack (expected 3, got 2)

    here also same problem

    1. delete the first underscore and comma, problem will be solved

    2. The code that you have used was used earlier. This code doesn't work with the current systems.
      Remove the first underscore and comma :

      (contours, _) = cv2.threshold(hand, 70, 255, cv2.THRESH_BINARY)

  4. image, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
    ValueError: not enough values to unpack (expected 3, got 2)

    please help!!

    1. The code you have used doesn't work these days.

      New Code :

      (contours, _) = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)

      Use the above code and you wil have your issue solved.

  5. all_image = np.hstack((drawing, crop_image))
    NameError: name 'drawing' is not defined

    please help!!!

  6. >>> contours,_ = cv2.findContours(the.copy(),cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
    Traceback (most recent call last):
    File "", line 1, in
    AttributeError: 'NoneType' object has no attribute 'copy'

    I m getting this error plz help me out