Intaglio Sketchpad is a full-featured drawing application designed for the iPad, iPhone and iPod touch, based on Intaglio, the award-winning Macintosh application. With most iPad and iPhone sketching apps you paint strokes or erase pixels on the screen. Intaglio Sketchpad is different because it allows you to create and edit shapes and text blocks. These graphic elements retain their shape and attributes and can be edited at any time. For example, you can adjust color, line thickness, or fix spelling mistakes at any time. To erase an element you simply select it and delete it without affecting whatever might be behind it.

Intaglio Sketchpad provides a full set of drawing tools and capabilities re-imagined for the multi-touch environment. For example, use one finger to draw or select a graphic, or use two fingers to rotate it. Hold your thumb on a tool button while drawing to constrain the object.

Features:

• Eleven drawing tools including freehand drawing, geometric shapes, bezier curve pen and text.
• Functions to align, delete, duplicate, group, layer or transform graphics.
• Create text using any font style in the iPhone OS (currently 58 font/style combinations on the iPhone and 110 on the iPad).
• Path editor, subpath contour control functions, boolean path operations and text to path conversion.
• Gradients, patterns, drop shadows, arrows, dashed lines, outlined text and clipping masks.
• Drawing aids such as a grid, smart guides and object location and size feedback.
• Customizable drawing scale and size.
• A customizable graphics library including a variety of predefined shapes.
• Multi-touch navigation with two finger scrolling and 800% zoom.
• Multiple levels of undo/redo.
• Import photos and scale or rotate them to composite with other graphics.
• Use cut, copy and paste to move graphics between drawings or export them to other apps.
• Import vector graphics from your computer as SVG.
• Export images to your photo library or as PDF, SVG, PNG or JPEG files to your computer via Wi-Fi or iTunes file sharing.
• Share drawings with other users of Sketchpad via Wi-Fi or Bluetooth, or with Intaglio on the Macintosh.

Snapchat and Instagram are the two mobile applications that literally blew away the community with their updates and innovations a number of times. The special filters that identify the faces in the picture are among the most significant innovative features. The feature receives an image through a smartphone camera’s lenses and puts funny elements over it (a dog face or a flower crown, for example), which is an implementation of the augmented reality technology (AR). In the given article, we will describe how Snapchat filters work, find out the basics of the Snapchat technology and describe the most common tools for the creation of software alike.

How Snapchat filters work: let’s begin with bare facts

For starters, let’s try to make sure that your application will be capable of bringing a decent profit after the release. In order to do that, you will have to analyze the MSQRD app development phenomenon.

Particularly, in the last few years, the filters have become quite a strong trend in the mobile software development sphere. Just check out the numbers – 1,6 million downloads of the MSQRD app, and that is only at the moment when Facebook decided to purchase it to repeat the success of the Snapchat facial recognition software (which engages around 173 million users with the smartphone’s screen daily). Impressed by the popularity of this type of software? We know that we are. Thus, let’s continue on with the principles of its creation.

How Snapchat filters work: general development principles

So, how to develop a face filter app? The first thing you will need to do is to choose the suitable API. The most commonly used ones among the developers are Google Cloud Vision API for Android, Google Mobile Vision iOS API, Microsoft Cognitive Services, and Core Image API. Let’s figure out by what principles they operate.

In particular, each API goes through two phases in order to recognize a face: image analysis phase and image processing phase. Let’s consider each in details.

The first phase is a quite complex one from the perspective of the used algorithms’ structure. The algorithms, in turn, are commonly applied in machine learning and require the application of the electronic Gaussian filter. Usually, to implement the phase, a combination of such methods is used – Histogram of Oriented Gradients and Support Vector Machine (note that they are applicable only to photos and are not able to recognize the faces in the turned on camera mode).

The first method divides the image into interconnected cells. The cells are analyzed in various scales and, based on the direction of the brim and intensity of the color gradient, it is defined whether a certain fragment features a face or not (the second method – SVM is used for that process). Then, after the face is identified, the analysis and recognition of its separate elements begin (of eyes, lips, brows, etc.). For that, the operation of the facial landmark detection is conducted (you can find out more details about this procedure in this article). The operation scans the part of an image with a face (the app identifies it as a fragment situated inside the restricting frame created via the previous methods) and indicates the precise coordinates of all the facial elements on the 2D plane.

The Viola-Jones method based on the computer vision can be used as an alternative to HOG and SVM. It employs cascade classifiers and is able to recognize the faces in real-time mode. You can find out more info on this method in this scientific article.

Thus, we received an image fragment constricted by the limiting frame which includes a human face with 2D coordinates that define the location of cheekbones, brows, eyes, mouth, and nose. The next processing stage for this fragment will be an augmentation of a certain virtual object – the so-called mask (on the example of Snapchat – a dog face or a flower crown). Again, the received facial landmarks are used for that. They make possible the situation of a new object in the required place and scaled accordingly (for instance, when a flower crown image is augmented, the software defines the location of a forehead and temporal region). Moving on, let’s get to practice and try to choose the best suitable library for the implementation of the above mentioned processes.

You will have to accept the fact that to date, not a single library composed using additional software tools can precisely locate the facial landmarks. Doesn’t matter what library we take – an extremely popular OpenCV or some other not that widely used option. Let’s take for an example one of the most renowned IT-companies out there – PixLab, which firmly holds the niche of a provider of mobile software that features advanced graphical technologies. According to its programmers team’s experience in the facial filters app development, the most productive results can be achieved using the combination of Dlib and MagickWand libraries.

Also, among the favorites of many developers are such libraries as Stasm (used to indicate the facial landmarks; in order to create the restricting frame, you will have to apply third-party software solutions), Cambridge Face Tracker (this library also requires additional tools for face recognition), GPUImage (compatible only with the iOS-based projects), and libccy (this library is used for face recognition but is unable to define the coordinates of the facial landmarks). You can figure out the best fitting option for your particular case only by trial and error.

Back to theory. What else is required to begin the face detection masks development

Suppose you successfully picked the tools. Are there any other guidelines that could help create filters for your augmented reality technology-based app? Yes, there are. We present our own list below. The listed features are guaranteed to make your application stand out among other software with similar functionality.

Use up-to-date masks design. It seems reasonable to enrich your solution with concepts actively employed by other apps. Namely, the all-encompassing cuteness overload and kawaii. On the other hand, you can go with a political topic and create masks inspired by the image of some media characters. For that purpose. employ the services of a separate graphical designers team closely familiar with the latest tendencies that will be able to create something unique and memorable for you.

Employ the latest graphical solutions. Do not limit your designers’ space for imagination. Let them realize the most insane (seeming at first) ideas. This approach to creating the new masks can, with a great probability, grant their increasing popularity.

Work with professionals. Independent development of a filter-rich app is a very presumptuous step. It is better to employ the help of experts who have successfully implemented several projects with a face detection feature as machine self-learning uses quite complex for understanding technologies. Remember – you do not get a second chance to prove yourself to your target audience.

Integrate your app with renowned social networks. It is very important to provide your users with the ability to share the processed photos with their friends. Remember to integrate your application with popular social networks for that purpose (such a feature can also make a registration process significantly easier).

How to make face tracking filters: summary

As we can see, the development of filters that work by the mechanics similar to Snapchat or Instagram face detection is not a simple process. Considering the colossal profit an app can potentially bring after the release, we strongly recommend you to employ a team of experts for its development.

When designing a business plan for a heavy load application, it is very important to take into account and accurately calculate such costs as the pricing of the hosting service where the application data will be stored. Large-scale applications, such as social networks, can become a real problem for their owners if the associated costs are calculated wrong initially.

Just imagine: thousands of users every day supplement the application database with messages, photos, and other media files – how much storage space is needed, how much can it cost and how much does a hosting server cost per user for a social network app? Will your application become a “dead” project because of the high maintenance expenses? In this article, we plan to describe the order of calculating the cost of server hosting for large applications to avoid unpleasant financial surprises after the app release.

What is the basis for calculating the average server cost per user?

It is important to keep in mind that server hostings are characterized not only by the provisioned storage space but also by communication channel bandwidth and hardware capacities. Thus, the mobile app backend hosting cost can be calculated based on the following indicators:

• – The cost of each storage gigabyte;
• – The cost of each megabit of bandwidth;
• – The cost of the server’s performance.

Also, the cost of server hosting can be affected by the equipment maintenance expenses, technical support charges, and other factors.

How to calculate the cost

How much does a social app cost to run? Depending on the pricing parameters, the cost of server hosting for a heavy application can be calculated in several ways.

Calculation according to the storage space cost

A very simple calculation scheme, for which it is required to approximate the number of application users and the maximum storage limits for each of them. The rough estimation is simple: if the cost of storing the object is $0.1 per GB of space per month and your application is calculated, say, for 5000 users, with a limit of 2 GB, the result of multiplying all the numbers (5000 × 2 × 0.1) the monthly cost of the server would be $1000.

It is important to understand that this calculation gives only an approximate cost of required hosting. The actual number of users may differ, and each user will not necessarily use all the space provided to them. Thus, you can make an assumption about the actual use of the server space (as a percentage of the initial number of users and disk space) and use this coefficient to adjust the appraisal.

Own / rented server

Buying or renting a whole server can significantly reduce the cost of hosting, but requires the seed capital. For example, for an application designed for the same 5000 users and 2 GB storage limit (10,000 GB or 10 TB), you need to purchase about 2 servers with 8x 2TB SATA disks (taking into account the cost of server space for user data, operating systems, application backend and RAID reservation), the cost of which is about $3000 each, plus additional equipment (racks, etc.), the totals would approximate to $6500. If you have such a starting amount, you can recoup the costs for 2 years at a server cost of $270-300 per month. Thus, the price of one GB of space for one user would equal to $0.06.

Making a long-term business plan with the calculation of hosting costs for the above scheme it is important to consider the expiration of the equipment. Any device has an approximate service life and needs regular replacement.

Another variant suitable for those who do not have sufficient starting capital is server equipment rental. Calculating the cost to maintain an application when renting server hardware can be carried out according to the same scheme, but taking into account the monthly rental fees.

Testing the application to determine the required hosting parameters

All the previous estimation methods are based only on the approximate assumptions of the user numbers and the necessary space for each user. Such calculations do not take into account the traffic, the required processor power, the average load on the server and many other factors. The calculation for these models is suitable for compiling a primary business plan for understanding the profitability of the application even before work on it is started.

However, in order to obtain more or less accurate data on the required server capacity and volume for an already developed application and, accordingly, calculate the cost of server hosting, a deeper approach is needed.

The best and accurate calculations are given by testing the required application efficiency using the specially developed software. Such test programs create “virtual users” that simulate the actions of real users of the application, measuring the loads to identify the optimal configuration of the application’s server part infrastructure.

The essence of the testing

To test the application architecture, worker threads mirroring virtual users are used, each of which can execute one of three action scenarios:

• – Light (authorization, login to the server, viewing the application partitions, sending/receiving requests);
• – Medium (to the light scenario’s actions, sending/receiving messages, uploading photos, viewing photos of other users, sending/receiving pictures are added);
• – Heavy (extensive exploitation of all the application features).

Typical time between each script action is established to 1 second.

Thus, gradually increasing the number of threads, each of which randomly engages one of the scenarios, the testing application measures the load on the server part of the application in its different configurations. As soon as any element of the application starts to work incorrectly, the test stops and changes the infrastructure configuration.

Most of the established outsourcing software development companies have such sophisticated in-house testing programs.

Results

The result of the test is the optimal configuration of the application infrastructure, which can support the maximum number of users simultaneously using the application. It also calculates the maximum hardware capabilities required for the application, based on which you can calculate the server hosting cost for the application most accurately.

Also, based on the results of the test, you can choose the hosting model (renting server hosting, renting server equipment or colocation, own server), which will not only be most advantageous financially but also meet the requirements of the application in the case of high loads.

Summary

When developing large applications similar to social networks, an important part of the business plan will be to estimate server costs per user. For preliminary calculations at the design stage of the application, you can employ simple mathematical models (number of users/space for each – to calculate hosting and storage costs/necessary equipment expenses/monthly fees – when buying or renting equipment).

However, for accurate calculations of the cost of hosting and choosing the most beneficial server interaction model (purchase, lease, colocation) in mobile development for Android or iOS, professional testing is necessary that would take into account all the appropriate factors. Only after calculating the necessary application load on the server can you tell exactly which server parameters will best meet the needs of the application and, based on the received data, clearly estimate the cost of hosting – total and average server cost per user.