Concepts in Computer Vision

Computer Vision Concepts

Computer Vision Concepts: A basic guide for beginners

Technological advances that give computers the ability to function like human eyes have come out in recent years. These advances include computer vision technologies that are now being integrated into laptops, mobile phones, and other electronic devices or equipment through the use of various e-commerce and software applications that are installed in those devices or equipment. The academic and business communities have been using these computer vision technologies to put their data to work in order to achieve more efficient operations in the electronics that they use.

In this article, we will discuss the basic concepts, terminologies, applications, and algorithms in computer vision to give you a better understanding of what concepts in computer vision is all about.

Image Processing

Although some may think that image processing is outside the range or scope of computer vision, both actually work very well together. Most applications that use computer vision rely mostly on image processing algorithms.

Common image processing techniques:

  • Exposure correction
  • Reduction of image noise
  • Straighten or rotation of image
  • Increase sharpness

Image processing is usually the first step in most computer vision systems. Computer vision uses concepts or techniques in image processing to preprocess image and transform this into a more appropriate data for further analysis.

A lot of techniques in image processing are being utilized in computer vision like linear and non-linear filtering, the Fourier transform, image pyramids and wavelets, geometric transformations, and global optimization.

Let’s take a look at some simple filtering techniques in image processing. Image filtering allows you to modify or clarify an image to extract the data that you need. I will use openCV and Python to demonstrate linear and non-linear filtering.

Linear Filtering
Linear filtering is a neighborhood operation which means that the output of a pixel’s value is decided by the weighted sum of the values of the inputted pixels.

Box filter
One example of linear filtering is the box filter which is very easy to implement.

Sample code to implement the box filter:

code implementation of linear filtering using box filter algorithm

Output of the code:

image output of linear filtering implementation using box filter algorithm

This implementation uses a kernel-based box blurring technique which is a built-in function in OpenCV. Applying the box filter to an image would result in a blurred image. We can see that process in the above image. In this implementation, we can set the size of the kernel – a fixed size array of numbers that has an anchor which is usually found at the center of the array.

Blog image of code snippet for concepts in computer vision and other technological advances.

Increasing the kernel size would result in a more blurred image because this implementation averages out the small neighborhood’s peak values where the kernel is applied.

Blog image for concepts in computer vision and other technological advances.

Initializing a kernel size with a smaller value would have no noticeable effect to an image because the kernel size is smaller than the actual size of the image.

Blog image for concepts in computer vision and other technological advances.

Blurring through Gaussian Filter
This is the most common technique for blurring or smoothing an image. This filter improves the result pixel found at the center and slowly minimizes the effects as pixels move away from the center. This filter can also help in removing noise in an image. For comparison, the box filter does not return a smooth blur on a photo with an object that has hard edges, while the Gaussian filter can improve this problem by making the edges around the object smoother.

OpenCV has a built-in function called GaussianBlur() that blurs an image using the Gaussian filter.

Sample code for Gaussian Filter:

code implementation of Gaussian filter algorithm

Output of the code:

image output of Gaussian filter algorithm

In this implementation, the kernel size is set to 5,5. The result is a blurred photo where strong edges are removed. We can see that this filter executed a more efficient blurring effect on the image than the box filter.

Non-Linear Filtering
Linear filtering is easy to use and implement. In some cases, this method is enough to get the necessary output. However, an increase in performance can be obtained through non-linear filtering. Through non-linear filtering, we can have more control and achieve better results when we encounter a more complex computer vision task.

Median Filtering
Median filter is an example of a non-linear filtering technique. This technique is commonly used for minimizing noise in an image. It operates by inspecting the image pixel by pixel and taking the place of each pixel’s value with the value of the neighboring pixel median.

Sample code for median filtering:

code implementation of median filtering algorithm

In this implementation, we used the OpenCV built-in function cv2.medianBlur() and passed a 50% noise to the input image to clearly see the effects of applying this filter.

Output of the code:

Full Scale image-5

image output of median filtering algorithm.

In the above image, we can see that the noise from the input image was reduced. This proves that median filtering technique is very effective in preventing noise (specifically salt and pepper noise) in an image.

Feature detection and matching

When it comes to concepts in computer vision, the feature detection and matching are one of the essential techniques in many computer vision applications. Some tasks involved in this technique are recognition, 3D reconstruction, structure-from-motion, image retrieval, object detection and many more.

This technique is usually divided into three tasks which are detection, description, and matching. In the detection task, points that are easy to notice or match are recognized in each image. In the description task, the aspect that surrounds each feature point is depicted in a way that it is unchanged in events like illumination, translation, scale, and in-plane rotation. In matching, for similar features to be classified, descriptors are being compared across images.

Some techniques in detecting and matching features are:

  • Lucas-Kanade
  • Harris
  • Shi-Tomasi
  • SUSAN (smallest univalue segment assimilating nucleus)
  • MSER (maximally stable extremal regions)
  • SIFT (scale invariant feature transform)
  • HOG (histogram of oriented gradients)
  • FAST (features from accelerated segment test)
  • SURF (speeded-up robust features)

Let’s demonstrate some of the popular feature detection and matching techniques (SIFT, SURF, ORB):

SIFT (Scale Invariant Feature Transform)
SIFT solves the problem of detecting the corners of an object even if it is scaled. Steps to implement this algorithm:

  • Scale space extrema detection – This step will identify the locations and scales that can still be recognized from different angles or view of the same object in an image.
  • Keypoint localization – When possible keypoints are located, they would be refined to get accurate results. This would result in the elimination of points that are low in contrast or points that have edges that are deficiently localized.
  • Orientation assignment – In this step, a consistent orientation is assigned to each key points to attain invariance when the image is being rotated.
  • Keypoint matching – In this step, the key points between images are now linked in order to recognize their nearest neighbors.

Sample code for implementing the SIFT algorithm:

code implementation of Sift algorithm

The above code is a simple implementation of detecting and drawing key points in openCV.

OpenCV can find the key points in an image using the function sift.detect(). Also, openCV can draw these key points to better visualize these points. The cv2.drawKeyPoints() function makes better visualization of these key points by drawing small circles on their locations.

This is the resulting image of the code:

image output of SIFT algorithm in computer vision

As we can see in the resulting image, the output shows the located key points of the inputted image.

OpenCV also provides us the function to calculate the descriptor. If we already found the key points of the image, we can utilize the function sift.compute() to compute the descriptor. If key points are not located, we can use the sift.detectAndCompute() to find the key points and compute the descriptor in one function.

SURF (Speeded-Up Robust Features)
Through SIFT, we can detect and describe key points of an object in an image. However, this algorithm is slow. So to solve this problem, a new algorithm was introduced which is now known as SURF short for Speeded-Up Robust Features. It is basically a sped up version of SIFT.

Basically, the implementation of the SURF algorithm using openCV is the same as implementing the SIFT algorithm. First, you need to create a SURF object using the function cv2.xfeatures2d.SURF_create(). You can also specify parameters to this function. We can detect keypoints using SURF.detect(), compute descriptor using SURF.compute and combine these two functions using SURF.detectAndCompute().

Sample for implementing the SURF algorithm in openCV:

code implementation of SURF algorithm in OpenCV

Original image:

original image to feed in SURF algorithm in OpenCV

Output of the code:

image output of SURF algorithm in OpenCV

We can see that SURF detects the white blobs in the Full Scale logo which somehow works like a blob detector. This technique can help in detecting some impurities of an image.

This algorithm is a great possible substitute to SIFT and SURF mainly because it performs better in computation and matching. It is a combination of fast keypoint detector and brief descriptor which contains a lot of alteration to improve performance. It is also a great alternative in terms of cost because the SIFT and SURF algorithms are patented which means that you need to buy them for their utilization.

Sample code for implementing the ORB algorithm:

code snippet of ORB Algorithm in computer vision

The implementation is basically the same as the first two algorithms that we implemented. We need to initialize an ORB object using cv2.ORB_create(). Then we can detect key points and compute the descriptor using the functions ORB.detect() and ORB.compute().

Output of the code:

The output of code implementation  using ORB Algorithm


In computer vision, segmentation is the process of extracting pixels in an image that are related. Segmentation algorithms usually take an image and produce a group of contours (boundary of an object that has well-defined edges in an image) or a mask where a set of related pixels are assigned to a unique color value in order to identify it.

Popular image segmentation techniques:

  • Active contours
  • Level sets
  • Graph-based merging
  • Mean Shift
  • Texture and intervening contour-based normalized cuts

Semantic Segmentation
The purpose of semantic segmentation is to categorize every pixel of an image to a certain class or label. In semantic segmentation, we can see what is the class of a pixel by simply looking directly at the color, but one downside of this is that we cannot identify if two colored masks belong to a certain object.

Instance Segmentation
In semantic segmentation, the only thing that matters to us is the class of each pixel. This would somehow lead to a problem that we cannot identify if that class belongs to the same object or not. Basically, semantic segmentation cannot identify if two objects in an image are separate entities. So to solve this problem, instance segmentation was created. This segmentation can identify two different objects of the same class. For example, if an image has two sheep in it, the sheep will be detected and masked with different colors in order to differentiate what instance of a class they belong.

Panoptic Segmentation
Panoptic segmentation is basically a union of semantic and instance segmentation.

In panoptic segmentation, every pixel is classified by a certain class and those pixels that have several instances of a class are also determined. For example, if an image has two cars, these cars will be masked with different colors. These colors represent the same class — car — but point to different instances of that certain class.


Recognition is one of the toughest challenges in the concepts in computer vision. Why is recognition hard? For the human eyes, recognizing an object’s features or attributes would be very easy. Humans can recognize multiple objects with very small effort. However, this does not apply for a machine. It would be very hard for a machine to recognize or detect an object because these objects vary. They vary in terms of viewpoints, sizes, or scales. Though these things are still challenges faced by most computer vision systems, they are still making advancements or approaches for solving these daunting tasks.

Object Recognition
Object recognition is used for indicating an object in an image or video. This is a product of machine learning and deep learning algorithms. Object recognition tries to acquire this innate human ability which is to understand certain features or visual detail of an image.

How does it work? There’s a lot of ways to perform object recognition. The most popular way of dealing with this is through machine learning and deep learning. These two algorithms are basically the same, but they differ in implementation.

Object recognition through deep learning can be achieved through training models or through utilizing pre-trained deep learning models. In order to train models from scratch, the first thing you need to do is to collect a large number of datasets. Then you need to design a certain architecture that will be used for creating the model.

Object recognition using deep learning may produce detailed and accurate results but this technique is very tedious because you need to collect a large number of data.

Just like in deep learning, object recognition through machine learning offers a variety of approaches. Some common machine learning approaches are:

  • HOG feature extraction
  • Bag of words model
  • Viola-Jones algorithm

Object Detection
Object detection in computer vision refers to the ability of machines to pinpoint the location of an object in an image or video. A lot of companies have been using object detection techniques in their system. They use it for face detection, web images, and security purposes.

In the concepts in computer vision, what is the difference between object recognition and object detection?? Object recognition answers the question: “Which object is rendered in the image?”. Object detection answers the question: “What is the location of an object in the image?”.

Object detection uses an object’s feature for classifying its class. For example, when looking for circles in an image, the machine will detect any object that is round. Basically, in order to recognize any instances of an object in a class, this algorithm uses learning techniques and extracted features of an image.

Listen to this episode

Hire software developers from Full Scale

One of the leading computer vision libraries in the market today is OpenCV – a cross-platform library where you can develop real-time computer-vision-applications and has C++, Python and Java interfaces. If you’re a software development company owner looking for remote software developers who can easily learn about OpenCV and other computer vision libraries and immediately apply them in their work, you can hire them from Full Scale – a leading offshore services provider of software development in Cebu City, Philippines.

Through our Guided Development system, we’ll provide you with a dedicated team of software developers who will work directly with you on a daily basis, and you will guide their development efforts. Our developers are proficient in C++, Python and Java – the major programming languages that support open source computer vision libraries. Contact us now to know more about how we can help your business to really take off, grow and expand!

Contact us now to start building your team!