In Recognition- based
CaRP, a password is a sequence of visual objects in the alphabet.
Recognition-based CaRP to have access to an infinite number of different visual
objects. Here there are three forms two recognition-based CaRP schemes and a
is a recognition-based CaRP scheme built on top of text Captcha. ClickText
alphabets should be clear without visually confusing characters. Consider
letter “O” and digit “0” which may cause confusion in CaRP images, so these
characters must be removed from the alphabet. A ClickText password is like text
password, a sequence of characters in the alphabet, e.g., ? = “AB#9CD87”. From
this, a ClickText image is generated by Captcha engine. While generating
ClickText image all the alphabet character’s position or location is tracked to
produce ground truth for the location of the character in the generated image.
Based on user- clicked points the authentication server relies on the ground
truth to identify the characters. In this ClickText images, characters can be
arranged randomly on 2D space. Whereas in text Captcha characters are aligned
from left to right for users to type them sequentially. ClickText image of an
alphabet of 33 characters shown in Fig. 2. Alphabets in user password are
clicked on the image with the password order, for example “A”, “B”, “#”, “9”,
“C”, “D”, “8”, and then “7” for password ? = “AB#9CD87”.