Inexpensive solution for real-time video and image stitching

Image stitching is the process of joining several images to obtain a bigger view of a scene. It is used, for example, in tourism to transmit to the viewer the sensation of being in another place. I am presenting an inexpensive solution for automatic real time video and image stitching with two web cameras as the video/image sources. The proposed solution relies on the usage of several markers in the scene as reference points for the stitching algorithm. The implemented algorithm is divided in four main steps, the marker detection, camera pose determination (in reference to the markers), video/image size and 3d transformation, and image translation. Wii remote controllers are used to support several steps in the process. The built‐in IR camera provides clean marker detection, which facilitates the camera pose determination. The only restriction in the algorithm is that markers have to be in the field of view when capturing the scene. Several tests where made to evaluate the final algorithm. The algorithm is able to perform video stitching with a frame rate between 8 and 13 fps. The joining of the two videos/images is good with minor misalignments in objects at the same depth of the marker,misalignments in the background and foreground are bigger. The capture process is simple enough so anyone can perform a stitching with a very short explanation. Although real‐time video stitching can be achieved by this affordable approach, there are few shortcomings in current version. For example, contrast inconsistency along the stitching line could be reduced by applying a color correction algorithm to every source videos. In addition, the misalignments in stitched images due to camera lens distortion could be eased by optical correction algorithm. The work was developed in Apple’s Quartz Composer, a visual programming environment. A library of extended functions was developed using Xcode tools also from Apple.

Plane Detection Using Affine Homography

AIRES, Kelson R. T.; ARAÚJO, Hélder J.; MEDEIROS, Adelardo A. D. Plane Detection Using Affine Homography. In: CONGRESSO BRASILEIRO DE AUTOMÁTICA, 2008, Juiz de Fora, MG: Anais... do CBA 2008.

Image processing algorithm for the identification of Martian dust devil tracks in MOC and HiRISE images

This paper presents a method for automatic identification of dust devils tracks in MOC NA and HiRISE images of Mars. The method is based on Mathematical Morphology and is able to successfully process those images despite their difference in spatial resolution or size of the scene. A dataset of 200 images from the surface of Mars representative of the diversity of those track features was considered for developing, testing and evaluating our method, confronting the outputs with reference images made manually. Analysis showed a mean accuracy of about 92%. We also give some examples on how to use the results to get information about dust devils, namelly mean width, main direction of movement and coverage per scene. (c) 2012 Elsevier Ltd. All rights reserved.

Detection and thinning of edges in previously known directions

This work presents a study on the generation of digital masks aiming at edge detection with previously known directions. This solution is important when edge direction is available either from a direction histogram or from a prediction based on camera and object models. A modification in the non-maximum suppression method of thinning is also presented enabling the comparison of local maxima for any edge directions. Results with a synthetic image and with crops of a CBERS satellite images are presented showing an example with its application in road detection, provided that directions are previously known.

IFTrace: Video segmentation of deformable objects using the Image Foresting Transform

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Accuracy of Digital Images in the Detection of Marginal Micro leakage: An In Vitro Study

Purpose: To evaluate the accuracy of Image Tool Software 3.0 (ITS 3.0) to detect marginal microleakage using the stereomicroscope as the validation criterion and ITS 3.0 as the tool under study.Materials and Methods: Class V cavities were prepared at the cementoenamel junction of 61 bovine incisors, and 53 halves of them were used. Using the stereomicroscope, microleakage was classified dichotomously: presence or absence. Next, ITS 3.0 was used to obtain measurements of the microleakage, so that 0.75 was taken as the cut-off point, and values equal to or greater than 0.75 indicated its presence, while values between 0.00 and 0.75 indicated its absence. Sensitivity and specificity were calculated by point and given as 95% confidence interval (95% CI).Results: The accuracy of the ITS 3.0 was verified with a sensitivity of 0.95 (95% CI: 0.89 to 1.00) and a specificity of 0.92 (95% CI: 0.84 to 0.99).Conclusion: Digital diagnosis of marginal microleakage using ITS 3.0 was sensitive and specific.

Edge detection and noise removal by use of a partial differential equation with automatic selection of parameters

This work deals with noise removal by the use of an edge preserving method whose parameters are automatically estimated, for any application, by simply providing information about the standard deviation noise level we wish to eliminate. The desired noiseless image u(x), in a Partial Differential Equation based model, can be viewed as the solution of an evolutionary differential equation u t(x) = F(u xx, u x, u, x, t) which means that the true solution will be reached when t ® ¥. In practical applications we should stop the time ''t'' at some moment during this evolutionary process. This work presents a sufficient condition, related to time t and to the standard deviation s of the noise we desire to remove, which gives a constant T such that u(x, T) is a good approximation of u(x). The approach here focused on edge preservation during the noise elimination process as its main characteristic. The balance between edge points and interior points is carried out by a function g which depends on the initial noisy image u(x, t0), the standard deviation of the noise we want to eliminate and a constant k. The k parameter estimation is also presented in this work therefore making, the proposed model automatic. The model's feasibility and the choice of the optimal time scale is evident through out the various experimental results.

Comparison of direct digital and conventional imaging with Ekta Speed Plus and INSIGHT films for the detection of approximal caries

Purpose: To evaluate the accuracy of approximal caries detection comparing enhanced and unenhanced Sidexis CCD-based digital image with Ektaspeed Plus and INSIGHT films. Methods: Fifty-two extracted premolars were imaged under identical standardized geometric and exposure conditions. Four observers, using five points confidence scale, rated 104 approximal surfaces for the presence or absence of carious lesions by means of four image modalities: (1) observer enhanced; (2) unenhanced Sidexis displays; (3) E speed films and (4) F speed film. Histologic sections served as validating criterion for the presence and depth of carious lesions. Diagnostic accuracy was measured as the area beneath the ROC curve. Results: Mean ROC (receiver operating characteristic) curve areas for approximal surfaces were 0.865 (E speed), 0.856 (F speed), 0.816 (unenhanced Sidexis) and 0.776 (observer enhanced). There were no significant differences between unenhanced digital Sidexis and films. Observer enhanced Sidexis images exhibited a statistically significant lower diagnostic accuracy than the film images for two of the observers.

Diagnostic agreement of conventional and inverted scanned panoramic radiographs in the detection of the mandibular canal and the mental foramen.

The aim of this study was to evaluate the diagnostic agreement of conventional panoramic radiographs and their inverted scanned images in the detection of the mandibular canal and mental foramen. A total of 77 panoramic radiographs obtained from the files of totally edentulous patients were used. Digitization was done by means of a scanner with brightness and contrast adjustment, as well as image inversion. The extension of mandibular canal was divided into anterior, middle, and posterior regions, and the presence of a radiopaque line that characterized the mandibular canal was classified according to a 5-point confidence scale. The mental foramen was classified in 4 types: continuous, separated, diffuse, and unidentified. Both conventional and inverted scanned panoramic radiographs were evaluated by 3 calibrated implantologists at 2 distinct moments with a minimum interval of 10 days between them. Intraexaminer agreement was evaluated by Kappa statistics by point and by 95% confidence interval. Because the intraexaminer level of agreement was low, interexaminer agreements could not be carried out. The results showed a substantial (in 2 situations), moderate (in 16 situations), and fair (in 18 situations) intraexaminer agreement for mandibular canal and a substantial (in 1 situation), fair (in 1 situation), and moderate (in 10 situations) intraeaminer agreement for mental foramen. There were no statistically significant differences in most instances. In conclusion, the diagnostic agreement of conventional and inverted scanned panoramic radiographs for detection of mandibular canal and mental foramen was low.

Adaptative techniques for the human faces detection

This paper presents results from an efficient approach to an automatic detection and extraction of human faces from images with any color, texture or objects in background, that consist in find isosceles triangles formed by the eyes and mouth.

Border detection in digital images: An approach by fuzzy numbers

The purpose of this paper is to introduce a new approach for edge detection in gray shaded images. The proposed approach is based on the fuzzy number theory. The idea is to deal with the uncertainties concerning the gray shades making up the image, and thus calculate the appropriateness of the pixels in relation to an homogeneous region around them. The pixels not belonging to the region are then classified as border pixels. The results have shown that the technique is simple, computationally efficient and with good results when compared with both the traditional border detectors and the fuzzy edge detectors. © 2007 IEEE.

Detection of highways in high resolution images using Mathematical Morphology techniques

This paper seeks to apply a routine for highways detection through the mathematical morphology tools in high resolution image. The Mathematical Morphology theory consists of describing structures geometric presents quantitatively in the image (targets or features). This explains the use of the Mathematical Morphology in this work. As high resolution images will be used, the largest difficulty in the highways detection process is the presence of trees and automobiles in the borders tracks. Like this, for the obtaining of good results through the use of morphologic tools was necessary to choose the structuring element appropriately to be used in the functions. Through the appropriate choice of the morphologic operators and structuring elements it was possible to detect the highways tracks. The linear feature detection using mathematical morphology techniques, can contribute in cartographic applications, as cartographic products updating.

Pitch detection algorithms based on zero-cross rate and autocorrelation function for musical notes

This paper discusses two pitch detection algorithms (PDA) for simple audio signals which are based on zero-cross rate (ZCR) and autocorrelation function (ACF). As it is well known, pitch detection methods based on ZCR and ACF are widely used in signal processing. This work shows some features and problems in using these methods, as well as some improvements developed to increase their performance. © 2008 IEEE.

Edge detection in digital images using fuzzy numbers

The purpose of this paper is to introduce a new approach for edge detection in grey shaded images. The proposed approach is based on the fuzzy number theory. The idea is to deal with the uncertainties concerning the grey shades making up the image and, thus, calculate the appropriateness of the pixels in relation to a homogeneous region around them. The pixels not belonging to the region are then classified as border pixels. The results have shown that the technique is simple, computationally efficient and with good results when compared with both the traditional border detectors and the fuzzy edge detectors. Copyright © 2009, Inderscience Publishers.

A regularized nonlinear diffusion approach for texture image denoising

In this paper a new partial differential equation based method is presented with a view to denoising images having textures. The proposed model combines a nonlinear anisotropic diffusion filter with recent harmonic analysis techniques. A wave atom shrinkage allied to detection by gradient technique is used to guide the diffusion process so as to smooth and maintain essential image characteristics. Two forcing terms are used to maintain and improve edges, boundaries and oscillatory features of an image having irregular details and texture. Experimental results show the performance of our model for texture preserving denoising when compared to recent methods in literature. © 2009 IEEE.