Holoentropy measures for image stitching of scenes acquired under CAMERA unknown or arbitrary positions

ABSTRACT:

Image stitching of similar scenes is a challenging task when scenes are captured under varying illuminations between the scenes, varying camera positions, varying orientations either in axial or azimuth. In this paper, we explore a seamless image stitching algorithm to address the above-said issues by applying techniques of dehazing on the acquired scenes and before identifying the image features and holoentropy aided feature matching on the Scale Invariant Feature Transform (SIFT) based features for the image. Experimentation of the proposed system is compared with the existing image stitching methods using squared distance, Minkowski and pairwise Euclidean distance for feature matching. The proposed seamless stitching method is evaluated based on the metrics, horizontal square gradient value (HSGV) and vertical square gradient value (VSGV). The obtained results are shown to be feasible for stitching the nonuniform or illumination variation multiple images. The exploration of above said stitching algorithm is intended to reduce the number of computations and inconsistencies in the stitched results.

PROJECT OUTPUT VIDEO:

EXISTING SYSTEM:

• Rosten et al. (2010) presented the FAST family of detectors. In addition, they turned the simple and repeatable segment test heuristic into the FAST-9 detector that has unmatched processing speed by machine learning. In spite of the design for speed, the resulting detector has excellent repeatability.

• Alahi et al. (2012) proposed a novel keypoint descriptor, which inspired by the human visual system and more accurately the retina, termed Fast Retina Keypoint (FREAK). A cascade of binary strings is calculated by efficiently comparing image intensities over a retinal sampling pattern.

DISADVANTAGES OF EXISTING SYSTEM:

• Chaotic noise

• Susceptible to Illumination Variant

• Sensitive to initial values and low dimensional data

• Prone to outlier and huge computational complexity

• Huge computational complexity

• Local searching characteristics

PROPOSED SYSTEM:

• The main intention of this proposed novel method is basically to address image stitching using images acquired with arbitrary and unknown camera positions that would result in image stitching challenges having varying scales, rotation and translations.

• The main contribution of this paper is Holoentropy aided feature matching: Feature matching based on the holoentropy scheme is introduced in this paper. The key points of the images to be stitched are determined using holoentropy because of the effective representation of nonlinear data and outlier removal characteristics.

• The noise tolerant behaviour of holoentropy helps to overcome the external influences on images in seamless stitching

ADVANTAGES OF PROPOSED SYSTEM:

• The proposed image stitching method helps noise removal so that the practical viabilities of the proposed method are increased.

• The features of the images are vital for accurate stitching of the images.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

• System           : Pentium Dual Core.

• Hard Disk       : 120 GB.

• Monitor          : 15’’ LED

• Input Devices : Keyboard, Mouse

• Ram                : 1GB.

SOFTWARE REQUIREMENTS:

• Operating system : Windows 7.

• Coding Language : MATLAB.

• Tool                      : MATLAB R2013A /2018

REFERENCE:

D. Ane Delphin a,⇑, Mahabaleswara R. Bhatt b, D. Thiripurasundari, “Holoentropy measures for image stitching of scenes acquired under CAMERA unknown or arbitrary positions”, Computer and Information Sciences (2018).