51Testing

Independent Software Testing Company

[51testing]

A Step-by-Step Guide of Localization Testing

Nowadays, many software is launched to different countries and regions, the process of adapting the software to the specific language, local customs, and culture is called localization. The test of this type is called localization testing.

[51testing]

Software testers do not make software; they only make them better.

Anonymous

[51testing]

A Complete Guide of Facial Recognition Testing

Scan your face to pay, scan your face to enter the subway, scan your face to punching… the era of traveling the world by just scanning your face is approaching. With the help of facial recognition, our lives become more flexible. How to verify the function, security, and recognition rate of facial recognition technology turn out to be the key topic in software testing. In this article, we will talk about facial recognition testing combining with a practical example.

So, if you want to know:

What is facial recognition?

What are use cases for face recognition?

How to test the facial recognition software?

Let’s get started.

What is facial recognition?

Facial recognition technology is a kind of biometric recognition technology based on facial features. It uses a camera to collect images or video containing human faces and automatically detects and tracks human faces. Facial recognition technology is divided into three parts: face detection, face tracking, and face comparison. We can detect the face of a living body in a complex background and scene through facial recognition and perform dynamic target tracking on the detected face in real-time. And compare the sampled facial image with the inventory face image sequentially and find the best match.

What are use cases for face recognition?

There are many use cases for facial recognition technology, such as the security management of enterprises and residences, identification and management of electronic passports and ID cards through biometric recognition, the government sectors use facial recognition to trace criminals, the bank ATM and computer login, etc. In general, face recognition is mostly used as identity verification for users which is usually divided into 1:1 face recognition and 1:n face recognition, etc. For example, 1:1 face recognition is mainly used to determine whether the person in the two photos is the same person. The model will give a score with the rule that the higher the score, the greater the possibility of being the same person. In reality, a threshold value M will set. If the score value is greater than the M, then the result is positive. In the same way, 1:n face recognition means that one face performs n-time 1:1 face recognition in the photo library, and finally matches the photo with the highest score in the face library.

How to test the facial recognition software?

1. The test standard

Take the facial recognition transfer as an example, we will test the connectivity, message format, invalid parameter verification, and return code, etc. Besides, facial recognition uses biometric technology and artificial intelligence algorithms and models. The transfer speed and result will be affected by the light, the background, the hairstyle, glasses, and other decorations. Although the model is built and trained perfectly, 100% accuracy is currently not guaranteed. Therefore, the standard divers in different sectors, the face recognition accuracy rate and pass criteria are determined by each domain. The general face recognition accuracy rate of the industry is greater than or equal to 99%. When the interface of the face recognition model can be successfully invoked, and the accuracy rate of recognition meets the standard requirements, it is deemed to have passed the test.

2. Test process

The following figure shows the main test process of a facial recognition model. Firstly, we need to prepare a certain amount of test data of two parts: one is a set of test materials, such as a pair of face photos, the other one is to tag label for the materials according to the model to be tested, that is, the matchup of face photos. After the data preparation is done, we can start testing.

A message requesting the service of the model is constructed for each test material and sent to the “face recognition service”, and compares the returned result with the label. After all the test data are been tested, calculate the accuracy rate, recall rate, misrecognition rate, and other indicators based on the result set to evaluate the tested model.

The focus of different models and use case divers, and the indicators are also different. In order to improve test efficiency, batch automatic testing is usually used by writing test scripts.

The test data is very important because, on the one hand, the number of data will influence the result. Too little data is prone to contingency. The result of the test sample has a greater impact on the model evaluation index. On the other hand, the test data should be “real”, fitting the real situation including the positive and negative examples. In order to be close to the use cases, you can prepare a photo collection(A) of daily life and a photo collection(B) of identification photos. When choosing the daily life photo, the ages, hats wearing, glasses-wearing, etc should be considered. And then tag the label of the two collections.

Considerations for facial recognition data

· Light and dark

· Hairstyle

· Whether to wear glasses?

· Whether to wear a hat?

· Whether the face is blocked?

· Is the face facing the camera?

· Background-color

· Whether there are other faces in the background?

· Face synthesis

· Other

Randomly select one photo from collection A and collection B, and send a request message for 1:1 facial recognition. A total of N*N request messages will be sent, of which two photos of N requests are the same person, which is called a positive example. And the photos in the remaining N*(N-1) requests are different people, which is called negative examples. Use the “N*N message” to request facial recognition, and compare the returned result with the tags. “misrecognition” refers that the 1:1 facial recognition model returns a high score, exceeding the threshold M, for two different person’s photos, that is, the negative examples is taken as the same person. The misrecognition rate is the percentage of misrecognized negative examples in total negative examples.

“Pass” refers to the 1:1 facial recognition model return back a high score for two photos of the same person, that is, the positive example is judged to be the same person. “Pass” means that the 1:1 face recognition model for two pictures of the same person returns a higher score, that is, the positive example is judged to be the same person; the “pass rate” refers to the percentage of the passed positive examples in the total positive examples. We hope that the misrecognition rate is 0%, and the pass rate is 100%. While the misrecognition rate and the pass rate are inseparable from the threshold M. if the threshold M is set low, the extreme case is set to 0, then the photos of different persons can be easily judged as the same person. The higher the threshold M is set, the less the possibility of misrecognition and passing, if the extreme case is set to 100, although the photos of different persons can be effectively recognized, the photos of the same person could not be recognized either, which influence the user experience. Therefore, there is a trade-off between the two when setting the threshold M. Since the threshold M has not been determined during the test, and considering 1:1 facial recognition is used for identity verification, which requires lower error-tolerant, the misrecognition rate can be confirmed first, and then the corresponding threshold M, finally the pass rate. The pass rate can be used as the evaluation index of the model. The calculation of test evaluation indicators is usually realized through automation, and test scripts are written to realize the whole process of constructing request messages, simulating sending, receiving and analyzing, recording results, and calculating evaluation indicators.

The above is the specific test method of face recognition technology, but actually, for different use cases and model characteristics, it is necessary to consider the test data and the selection of model evaluation indicators in combination with actual conditions.

[51testing]

Quality is never an accident; it is always the result of intelligent effort.

 John Ruskin

[51testing]

Exploratory Testing in Game Testing

The game test is actually mainly manual testing. When it comes to manual testing, it will definitely talk about exploratory testing.

The Definition of Exploratory Testing

“ What is exploratory testing?

EXPLORATORY TESTING is a type of software testing where test cases are not created in advance but testers check the system when processing. The focus of exploratory testing is more on testing as a “thinking” activity. ”

The test methods mentioned in the book Exploratory Testing are very useful for game testing. And this is what we will share today.

Guide Test Method

It is to review the functions strictly in accordance with the plan. This is the most basic and most important method.

Selling Point Test Method

This method is to encourage testers to watch the demo from the point of view of sales and understand the biggest selling point of the game. The selling point is not necessarily the core function of the game, but it must be given the same attention as the core function. For example, the biggest selling point of the mobile game “League of Goddess” is naturally the goddess, but the goddess is not the core function of the game, but auxiliary gameplay, but players are keen on this, it is very necessary to test more.

Landmark Test Method

The method is that if we want to go to a place, we usually set the flags representing the steps on the map, but no one stipulates where we should follow the steps. Since there are quite a lot of related functions in the game, the landmark test method can be said to be a very commonly used method when we test. For example, if the player kills a monster, the player will get +1 experience point(EXP). Will the player gain EXP by just hitting the last monster? Will the player gain experience point when the monster is killed while also dying?

Limit Test Method

Test the limit of the functional program. For example, one hundred players attacked a monster at the same time and check the result.

Late Night Test Method

This method is mainly used for some functions such as data backup and has little connection with game testing.

Museum Test Method

This method is used for long-term projects. Some old functions have been running normally. After new functions are released, whether the old functions are still normal.

Deep Alley Test Method

This method is mainly used for observing some points where no one pays attention, such as the function of HELP.

Overnight Test Method

This method is used to checking whether the function is normal when it runs continuously for a long time.

Long Path Test Method

Check the result that requires the most operation steps, and every step to reach this result.

Supermodel Test Method

You may think this method not very useful at first glance, isn’t it just looking at the interface? I watch it every day. But in fact, it is different to look at the interface with the mentality of finding bugs. For example, I look at an enhanced interface every day, but until I plan to find bugs, I really discovered that the tabbed text on this interface is a few pixels crooked compared to the text on other tabs. This is what I haven’t noticed before. Interface in the game is a very important thing, so the use of supermodel testing is of great help to us.

Cancel Test Method

Close the operation interface, close the application, switch the line when the program is processing to check whether there is bugs.

Sluggard Test Method

Choose the most trouble-free step to achieve the result, and check whether the result is correct.

Obsessive-compulsive Disorder Test Method

Keep repeating the operation to check whether the function responds normally. I think the most likely thing in the game is to use a mouse simulator to continuously click.

We use different methods to test different games and it is necessary to keep summarizing which methods are often used in the games.

For test engineers looking for game testing jobs, it is necessary to accumulate different game testing methods. For exploratory testing in game testing, I think that the methods mentioned above are very helpful. In software testing, you can use brain maps to write test methods and use cases. The more you write, the more proficient you will be.