We conduct an exhaustive survey of image thresholding methods, categorize them, express their formulas under a uniform notation, and finally carry their performance comparison. The thresholding methods are categorized according to the information they are exploiting, such as histogram shape, measurement space clustering, entropy, object attributes, spatial correlation, and local gray-level surface. 40 selected thresholding methods from various categories are compared in the context of nondestructive testing applications as well as for document images. The comparison is based on the combined performance measures. We identify the thresholding algorithms that perform uniformly better over nonde- structive testing and document image applications. © 2004 SPIE and IS&T. (DOI: 10.1117/1.1631316)

/pdf/survey-over-image-thresholding-techniques-and-quantitative-2ekadyqjhj.pdf

Survey over image thresholding techniques and quantitative performance evaluation

A review on image segmentation techniques

As a practical and effective tool for quantitative in-plane deformation measurement of a planar object surface, two-dimensional digital image correlation (2D DIC) is now widely accepted and commonly used in the field of experimental mechanics. It directly provides full-field displacements to sub-pixel accuracy and full-field strains by comparing the digital images of a test object surface acquired before and after deformation. In this review, methodologies of the 2D DIC technique for displacement field measurement and strain field estimation are systematically reviewed and discussed. Detailed analyses of the measurement accuracy considering the influences of both experimental conditions and algorithm details are provided. Measures for achieving high accuracy deformation measurement using the 2D DIC technique are also recommended. Since microscale and nanoscale deformation measurement can easily be realized by combining the 2D DIC technique with high-spatial-resolution microscopes, the 2D DIC technique should find more applications in broad areas.

https://iopscience.iop.org/article/10.1088/0957-0233/20/6/062001/pdf

Two-dimensional digital image correlation for in-plane displacement and strain measurement: a review

A scheme is developed for classifying the types of motion perceived by a humanlike robot. It is assumed that the robot receives visual images of the scene using a perspective system model. Equations, theorems, concepts, clues, etc., relating the objects, their positions, and their motion to their images on the focal plane are presented. >

http://ieeexplore.ieee.org/iel2/815/3148/00100651.pdf

Robot vision

One of the challenges in 3D shape matching arises from the fact that in many applications, models should be considered to be the same if they differ by a rotation. Consequently, when comparing two models, a similarity metric implicitly provides the measure of similarity at the optimal alignment. Explicitly solving for the optimal alignment is usually impractical. So, two general methods have been proposed for addressing this issue: (1) Every model is represented using rotation invariant descriptors. (2) Every model is described by a rotation dependent descriptor that is aligned into a canonical coordinate system defined by the model. In this paper, we describe the limitations of canonical alignment and discuss an alternate method, based on spherical harmonics, for obtaining rotation invariant representations. We describe the properties of this tool and show how it can be applied to a number of existing, orientation dependent descriptors to improve their matching performance. The advantages of this tool are two-fold: First, it improves the matching performance of many descriptors. Second, it reduces the dimensionality of the descriptor, providing a more compact representation, which in turn makes comparing two models more efficient.

/pdf/rotation-invariant-spherical-harmonic-representation-of-3d-1xmyw7hacf.pdf

Rotation invariant spherical harmonic representation of 3D shape descriptors

An alternative approach to fully automatic speckle-displacement measurement is described. Two speckle patterns of a specimen, one before and one after deformation, are captured by a CCD camera and registered by a frame grabber. Two series of small subimages are obtained by segmenting the two speckle patterns. The corresponding subimage pairs extracted from both series are analyzed pointwise. The interrogation of each subimage pair involves a two-step fast-Fourier transform. While the first-step fast-Fourier transform achieves a complex spectrum characterized by the local displacement information, the second-step one generates a signal peak in the second spectral domain that resolves the local displacement vector. A rough estimate of the displacement vector is achieved by detecting the maximum pixel of the discrete spectrum. A more accurate determination is attained by a subpixel-maximum determination through a biparabolic fitting near the signal peak. The u- and v-displacement fields are deduced by analyzing all subimage pairs. A large rigid-body displacement can be overcome by introducing an artificial rigid shift of the two speckle patterns toward each other before the numerical process. The technique retains all the advantages of optical speckle photography and provides an extended range of measurement. Dynamic incremental deformations can be inspected by registering more speckle patterns at many consecutive deformation stages by using a high-speed CCD camera. The system was applied successfully to the study of crack-tip deformation fields.

Digital speckle-displacement measurement using a complex spectrum method

The 3-D moment method is applied to object identification and positioning. A general theory of deriving 3-D moments invariants is proposed. The notion of complex moments is introduced. Complex moments are defined as linear combinations of moments with complex coefficients and are collected into multiplets such that each multiplet transforms irreducibly under 3-D rotations. The application of the 3-D moment method to motion estimation is also discussed. Using group-theoretic techniques, various invariant scalars are extracted from compounds of complex moments via Clebsch-Gordon expansion. Twelve moment invariants consisting of the second-order and third-order moments are explicitly derived. Based on a perturbation formula, it is shown that the second-order moment invariants can be used to predict whether the estimation using noisy data is reliable or not. The new derivation of vector forms also facilities the calculation of motion estimation in a tensor approach. Vectors consisting of the third-order moments can be derived in a similar manner. >

3-D moment forms: their construction and application to object identification and positioning

The feasibility of applying image processing techniques to metal surface inspection is demonstrated. Two methods for metal surface inspection are described. In the first method, the metal surface reflective power and the metal surface normal are related by a random surface scattering model. The metal surface profile can then be computed from the metal surface normal. The second method applies pattern recognition techniques to classify metal surfaces into classes of different roughness. Methods of feature extraction and classification have been tested experimentally and the performances of different types of classifier have been compared. A two-level tree classifier using nonparametric linear classifiers at each node gives better than 90% correct classification on the testing set.

Metal surface inspection using image processing techniques

An exponential bidirectional associative memory (eBAM) using an exponential encoding scheme is discussed. It has a higher capacity for pattern pair storage than conventional BAMs. A new energy function is defined. The associative memory takes advantage of the exponential nonlinearity in the evolution equations such that the signal-to-noise ratio (SNR) is significantly increased. The energy of the eBAM decreases as the recall process proceeds, ensuring the stability of the system. The increase of SNR consequently enhances the capacity of the BAM. The capacity of the exponential BAM is estimated. >

An analysis of high-capacity discrete exponential BAM

A new thresholding method, called Noise Attribute Thresholding method (NAT), for document processing is presented. This method has overcome a difficulty encountered by many conventional global thresholding methods which utilize the image gray level histogram. The difficulty is that some objects of interest in the image do not form prominent peaks in the histogram. The NAT method utilizes the noise attribute features extracted from the image. These features are based on a simple noise model and are independent of the strength of the signals (objects) in the image. Experimental results show that this method is very effective.

Hon-Son Don

Papers

Digital speckle-displacement measurement using a complex spectrum method

3-D moment forms: their construction and application to object identification and positioning

Metal surface inspection using image processing techniques

An analysis of high-capacity discrete exponential BAM

A noise attribute thresholding method for document image binarization