Pupil Detection by Alternative Approach by Exploiting Intensity Parameters As Well As

Pupil Detection by Alternative Approach by Exploiting Intensity Parameters As Well As

Pupil Detection by alternative Approach by exploiting Intensity Parameters as well as Dimensional Characteristics

Arun Sharma, Assistant Professor

University Institute of Engineering & Technology,

Kurukshetra University, Kurukshetra, Haryana, India.

Abstract-In present day world when identity circumferences many social, personal, professional outlooks, the identification of identity is highly critical. In pursuit of the same if we consider biological identity of person as a resource to identify his identity, we are approaching towards a new arena of a metric system call biometric system which enables us for automatic identification of an individual based on a unique feature or characteristic biologically possessed by the individual. Iris recognition is one of the celebrated technologies which are frequently finding its way into human life. Pupil detection is the foremost step for iris recognition with MATLAB software version 2010b as the novel method to improve feature extraction.

Keywords- Iris Recognition, coordinates, intensity, co-centric,biometric, test/real-time input.


Iris recognition is an automated method of biometric identification that uses mathematical pattern-recognition techniques on images of the iris of an individual's eyes, whose complex random patterns are unique and can be seen from some distance. [1,2]

The first phase of iris biometric systems is capturing the sample of the iris. Then iris samples are pre-processed and segmented to locate the iris. Once the iris is located, it is then normalized from polar coordinate to Cartesian [3,4]. Next, a template representing a set of features from the iris is generated. The iris template can then be objectively compared with other templates in order to determine an individual's identity. [5,6] This paper presents the novelty involved in first step for the segmentation pupil by determining coordinates of image

Digital images are prone to a variety of types of noise. Noise is the result of errors in the image acquisition process that result in pixel values that do not reflect the true intensities of the real scene. There are several ways that noise can be introduced into an image, depending on how the image is created. For example:

If the image is scanned from a photograph made on film, the film grain is a source of noise. Noise can also be the result of damage to the film, or be introduced by the scanner itself.

If the image is acquired directly in a digital format, the mechanism for gathering the data (such as a CCD detector) can introduce noise.Electronic transmission of image data can introduce noise. [7,8].


After loading the image this part of the paper deals with pupil detection module. A set of nine sample images all different to each other in their features. First five sample images show pupil detection with success while next four images show error as shown in last image of this module. The error is due to the fact that in present work we have used the image processing module detecting the set of pixels with approximately representing a circular region while in last four images as the pixels representing eyelashes and pupil are mingled together, it takes the view of a semicircle attached with an arc shape portion above it.

The captions taken by implementing the present work is given below as:

  1. Load Iris Image

Fig. 1: loaded sample image of iris

  1. Convert color image or grey image to binary image.
  2. Replaces all pixels in the input image with luminance greater than level with the value 1 (white) and replaces all other pixels with the value 0 (black). Specify level in the range [0, 1]. This range is relative to the signal levels possible for the image's class. Therefore, a level value of 0.5 is midway between black and white, regardless of class.

Input: Color Image or Grey Scale

Output: Centre of Pupil

1. X-coordinates of centre

2. Y-coordinates of centre

3. Radius of Pupil

4.X-coordinates of radius of Pupil

5.Y-coordinates of radius of Pupil

Fig. 2: Pupil detection module

  1. In our case, we have generalized the threshold limit to the half of the pixel intensity of grey scale image.
  2. Create a morphological disk structuring element. A flat, disk-shaped structuring element.
  3. Produce a binary image.
  4. Selecting a predefined threshold and employing intensity criteria loop over the boundaries.
  5. Set the relevant threshold according to the data base and put the recent output image into loop to trace the exterior boundaries of objects. Image must be a binary image where nonzero pixels belong to an object and 0 pixels constitute the background.
  6. Mark objects above the threshold with a black circle.

Fig. 3: Isolated portion of pupil from sample image

Fig. 4: Boundary drawn on pupil from sample image

  1. Isolating the pupil from image, calculate the center and radius of pupil.

The MATLAB simulation results for various standard images are as follows:

Figure 5: Pupil detection (sample image 1)

Figure 6: Pupil detection (sample image 2)

Figure 7: Pupil detection (sample image 3)

Figure 8: Pupil detection (sample image 4)

Figure 9: Pupil detection (sample image 5)

Figure 10: Pupil detection (sample image 6)

Figure 11: Pupil detection (sample image 7)

Figure 12: Pupil detection (sample image 8)

Figure 13: Pupil detection (sample image 9)

Figure 14: Error occurred in pupil detection for sample image 6,7,8,9.


The pupil detection is effectively implemented for standard images by alternative approach by exploiting intensity parameters as well as dimensional characteristics. Future work corresponds to effectively overcome the images where eyelids touch the pupil.


[1]Jain, A., Hong, L., &Pankanti, S. “Biometric Identification"Communications”of the ACM, 43(2),2000.

[2]Jain, Anil K.; Ross, Arun"Introduction to Biometrics". In Jain, AK; Flynn, P; Ross, A. Handbook of Biometrics.Springer. pp.1–22. ISBN978-0-387-71040-2,2008.

[3]Jain, A.K.; Bolle, R.; Pankanti, S., eds. “Biometrics: Personal Identification in Networked Society”. Kluwer Academic Publications, 1999.

[4]Sahoo, SoyujKumar; MahadevaPrasanna, SR, Choubisa, Tarun"Multimodal Biometric Person Authentication: A Review". IETE Technical Review29 (1): 54. retrieved 23 February 2012.

[5]A. Rattani, "Adaptive Biometric System based on Template Update Procedures," PhD thesis, University of Cagliari, Italy, 2010

[6]A. Rattani, B. Freni, G. L. Marcialis and F. Roli,"Template update methods in adaptive biometric systems: a critical review," 3rd International Conference on Biometrics, Alghero, Italy, pp. 847-856, 2009.

[7]N. K. Ratha, J. H. Connell, and R. M. Bolle, "Enhancing security and privacy in biometrics-based authentication systems," IBM systems Journal, vol. 40, pp. 614–634, 2001.