CS632

An object appears white to observer when it reflects light relatively balanced in all visible wavelengths of EM energy. True. False.

Light that is void of color is named chromatic light. True. False.

The only attribute of monochromatic light is its intensity or amount. True. False.

Luminance is a subjective descriptor (that is practically impossible to measure) of reflected or absorbed light perception from an object by an observer, and it is affected by the background. True. Flase.

Machines prefer their images for processing to be detailed and cluttered. True. Flase.

In the mid-level processing of images, the input is image and output is attributes. True. False.

Noise removal is one of the most important areas in low-level processing of images. True. False.

The algorithms of high-level processing are the most complex. True. False.

In CCD camera, a single row of sensors is moved across the image, capturing it row-by-row as the row moves. True. False.

Digitizing the spatial coordinate's values of a captured image is named image quantization. True. False.

Resolution is measure of how much the detail of an image could be seen or perceived. True. False.

Quantization resolution is measure of the smallest perceptible change in intensity level in image, and it is dependent on the used number of quantization levels. True. False.

If intensity quantization levels are not enough, checkerboards effect can occur in image. True. False.

The number of dots (pixels) per unit distance measures pixel depth. True. False.

15. As the dynamic range of an image increases as the contrast of the image decreases. True. False.

Noise is the highest value beyond which all intensity levels are clipped. True. False.

Black and white image stores pixel values in 2-bits. True. False.

Image compression is one of the computer vision applications. True. False.

Image restoration is subjective process where the observer is the only judger of its output. True. False.

M-adjacency is introduced to eliminate the ambiguities that arise when 4-adjacency is used. True. False.

Edge concept is local that is based on a measure of intensity-level discontinuity at a pixel. True. False.

Boundary of a finite region forms a closed path. True. False.

Most of the arithmetic operations performed on images are matrix-based. True. False.

Nonlinear operators are based on a large body of theoretical and practical results. True. False.

Max operator is mathematically nonlinear. True. False.

The visual evaluation of enhanced image quality is a highly objective process. True. False.

Image Enhancement methods are very much problem oriented. True. False.

Frequency domain enhancement methods are based on direct manipulation of image pixels. True. False.

Intensity transformation and histogram based enhancement methods operate on one image. True. False.

Arithmetic enhancement operations may be performed between an image and a constant. True. False.

The log-transformation method is also named the gamma transform. True. False.

Gray-level slicing is a type of mathematical gray-level transformation methods. True. False.

The smoothing filters are useful for highlighting fine details in images. True. False.

Spatial mask-based enhancement methods consist of moving an odd-sized filter that maps to the rectangular neighborhood area, form pixel to pixel in the original input image. True. False.

The approach of truncating missed edge pixels at filtering only works with some filters and itcan add extra code and slow down processing. True. False.

In nonlinear spatial filtering, the filter response is calculated by the sum of products of the. True. False.

The weights of the smoothing mask must be positive and their sum after normalization is 1. True. False.

Sharpening is useful for reducing noise, suppressing edges and eliminating small details. True. False.

Blurring produced by weighted average filter is less than that produced by average filter. True. False.

As σ of Gaussian filter decreases, more smoothing occurs by the Gaussian filter. True. False.

Separable 2D kernel gives more computational saving than 2D non-separable kernel. True. False.

Sharpening spatial filters can be represented by partial derivatives. True. False.

Applying unsharp filter to an image, getting a new image that highlights grayish edges and other discontinuities on dark featureless background. True. False.

rotating the image and applying the Laplacian filter gives the same result as applying the Laplacian filter and then rotating the image. True. False.

The visible color spectrum is divided into ……… broad regions. three. four. five. six.

. .......... basic quantities are used to describe the quality of chromatic light source. three. four. five. six.

……… is the total amount of energy that flows from the light source, and it is usually measured in watts. Radiance. Luminance. Brightness. None of Above Choices.

The continuum from image processing to computer vision can be broken up into ……… levels. three. four. five. six.

Segmentation of objects in image is considered …….. –level vision. low. mid. high. no.

The 2D Image function may be mathematically characterized by ………. components. two. three. four. five.

Each pixel is commonly stored in one byte to represent the shades of gray in ………. Image. binary. monochrome. color. indexed.

There are ……… types of image compression. two. three. four. five.

Image ……… aims to invert known or estimated degradation to images. enhancement. restoration. compression. segmentation.

. ………-neighborhood relation considers only the vertical and horizontal neighbors. Four. Diagonal. Six. Eight.

Due to storage and quantizing hardware considerations, the number of intensity quantization. square root. logarithm. exponential. power.

. ……….-distance is also called city-block distance. De. D4. D8. Dm.

The pixels having a D8-distance from a pixel (x,y) are less than or equal to some value r from a …….. centered at (x,y). disk. diamond. square. triangle.

You studied that any linear operator must satisfy ……… properties. two. three. four. five.

Spatial image enhancement methods are divided into ………. two. three. four. five.

Point processing-based enhancement methods are divided into ………. two. three. four. five.

Intensity transformation-based enhancement methods are divided into ………. two. three. four. five.

Histogram-based enhancement methods are divided into ………. two. three. four. five.

All of the following choices are point processing-based enhancement operations performed between the corresponding pixels of two images of the same size, except ……… operations. arithmetic. set. logical. transformation.

Arithmetic enhancement operations are divided into ………. two. three. four. five.

The …………. transformation is used to expand the values of dark pixels in an image while. negative. logarithmic. exponential. gamma.

Image-by-image ………. technique is often sufficient to yield an accurate outline of the moving object in a sequence of images. addition. subtraction. multiplication. division.

Histogram ……… is an automatic enhancement method in which the required transformation of the input image is derived from a pre (an user)-specified reference histogram that is taken from any arbitrary image of a similar kind that not necessarily being of the same size. matching. equalization. look-up. stretching.

……… approach deals with missing edge pixels in a spatial local enhancement method by typically substituting them with either all white or all black pixels. Omitting. Padding. Replication. Truncation.

Spatial neighbourhood-based enhancement methods are ………. two. three. four. five.

. ………. filter applies first smoothing for performing its sharpening task. Laplacian. Simplified. Unsharp. Gaussian.

Laplacian operator is isotropic which means that it is ……….-invariant. intensity. translation. rotation. shape.

………. filter is linearly separable, so it can be expressed as the matrix product of a column vector with a row vector. Gaussian. Weighted-Average. Laplacian. Unsharp.

A disadvantage of ……… is that “block artifacts” can occur at the boundaries between the tiles as a result of processing each such tile in isolation which gives impression of an image consisting of a number of slightly incompatible blocks. binary histogram equalization. color histogram equalization. adaptive histogram equalization. intensity histogram equalization.