Recherche avancée

Sur d’autres sites (5376)

• Developing MobyCAIRO

  26 mai 2021, par Multimedia Mike — General

  I recently published a tool called MobyCAIRO. The ‘CAIRO’ part stands for Computer-Assisted Image ROtation, while the ‘Moby’ prefix refers to its role in helping process artifact image scans to submit to the MobyGames database. The tool is meant to provide an accelerated workflow for rotating and cropping image scans. It works on both Windows and Linux. Hopefully, it can solve similar workflow problems for other people.

  As of this writing, MobyCAIRO has not been tested on Mac OS X yet– I expect some issues there that should be easily solvable if someone cares to test it.

  The rest of this post describes my motivations and how I arrived at the solution.

  Background
  I have scanned well in excess of 2100 images for MobyGames and other purposes in the past 16 years or so. The workflow looks like this :

  
  

  

  Image workflow

  
  

  It should be noted that my original workflow featured me manually rotating the artifact on the scanner bed in order to ensure straightness, because I guess I thought that rotate functions in image editing programs constituted dark, unholy magic or something. So my workflow used to be even more arduous :

  
  

  

  I can’t believe I had the patience to do this for hundreds of scans

  
  

  Sometime last year, I was sitting down to perform some more scanning and found myself dreading the oncoming tedium of straightening and cropping the images. This prompted a pivotal question :

  
  Why can’t a computer do this for me ?
  

  After all, I have always been a huge proponent of making computers handle the most tedious, repetitive, mind-numbing, and error-prone tasks. So I did some web searching to find if there were any solutions that dealt with this. I also consulted with some like-minded folks who have to cope with the same tedious workflow.

  I came up empty-handed. So I endeavored to develop my own solution.

  Problem Statement and Prior Work
  
  I want to develop a workflow that can automatically rotate an image so that it is straight, and also find the most likely crop rectangle, uniformly whitening the area outside of the crop area (in the case of circles).

  As mentioned, I checked to see if any other programs can handle this, starting with my usual workhorse, Photoshop Elements. But I can’t expect the trimmed down version to do everything. I tried to find out if its big brother could handle the task, but couldn’t find a definitive answer on that. Nor could I find any other tools that seem to take an interest in optimizing this particular workflow.

  When I brought this up to some peers, I received some suggestions, including an idea that the venerable GIMP had a feature like this, but I could not find any evidence. Further, I would get responses of “Program XYZ can do image rotation and cropping.” I had to tamp down on the snark to avoid saying “Wow ! An image editor that can perform rotation AND cropping ? What a game-changer !” Rotation and cropping features are table stakes for any halfway competent image editor for the last 25 or so years at least. I am hoping to find or create a program which can lend a bit of programmatic assistance to the task.

  Why can’t other programs handle this ? The answer seems fairly obvious : Image editing tools are general tools and I want a highly customized workflow. It’s not reasonable to expect a turnkey solution to do this.

  Brainstorming An Approach
  I started with the happiest of happy cases— A disc that needed archiving (a marketing/press assets CD-ROM from a video game company, contents described here) which appeared to have some pretty clear straight lines :

  
  
  

  My idea was to try to find straight lines in the image and then rotate the image so that the image is parallel to the horizontal based on the longest single straight line detected.

  I just needed to figure out how to find a straight line inside of an image. Fortunately, I quickly learned that this is very much a solved problem thanks to something called the Hough transform. As a bonus, I read that this is also the tool I would want to use for finding circles, when I got to that part. The nice thing about knowing the formal algorithm to use is being able to find efficient, optimized libraries which already implement it.

  Early Prototype
  A little searching for how to perform a Hough transform in Python led me first to scikit. I was able to rapidly produce a prototype that did some basic image processing. However, running the Hough transform directly on the image and rotating according to the longest line segment discovered turned out not to yield expected results.

  
  
  

  It also took a very long time to chew on the 3300×3300 raw image– certainly longer than I care to wait for an accelerated workflow concept. The key, however, is that you are apparently not supposed to run the Hough transform on a raw image– you need to compute the edges first, and then attempt to determine which edges are ‘straight’. The recommended algorithm for this step is the Canny edge detector. After applying this, I get the expected rotation :

  
  
  

  The algorithm also completes in a few seconds. So this is a good early result and I was feeling pretty confident. But, again– happiest of happy cases. I should also mention at this point that I had originally envisioned a tool that I would simply run against a scanned image and it would automatically/magically make the image straight, followed by a perfect crop.

  Along came my MobyGames comrade Foxhack to disabuse me of the hope of ever developing a fully automated tool. Just try and find a usefully long straight line in this :

  
  

  Darn it, Foxhack…
  

  There are straight edges, to be sure. But my initial brainstorm of rotating according to the longest straight edge looks infeasible. Further, it’s at this point that we start brainstorming that perhaps we could match on ratings badges such as the standard ESRB badges omnipresent on U.S. video games. This gets into feature detection and complicates things.

  This Needs To Be Interactive
  At this point in the effort, I came to terms with the fact that the solution will need to have some element of interactivity. I will also need to get out of my safe Linux haven and figure out how to develop this on a Windows desktop, something I am not experienced with.

  I initially dreamed up an impressive beast of a program written in C++ that leverages Windows desktop GUI frameworks, OpenGL for display and real-time rotation, GPU acceleration for image analysis and processing tricks, and some novel input concepts. I thought GPU acceleration would be crucial since I have a fairly good GPU on my main Windows desktop and I hear that these things are pretty good at image processing.

  I created a list of prototyping tasks on a Trello board and made a decent amount of headway on prototyping all the various pieces that I would need to tie together in order to make this a reality. But it was ultimately slowgoing when you can only grab an hour or 2 here and there to try to get anything done.

  Settling On A Solution
  Recently, I was determined to get a set of old shareware discs archived. I ripped the data a year ago but I was blocked on the scanning task because I knew that would also involve tedious straightening and cropping. So I finally got all the scans done, which was reasonably quick. But I was determined to not manually post-process them.

  This was fairly recent, but I can’t quite recall how I managed to come across the OpenCV library and its Python bindings. OpenCV is an amazing library that provides a significant toolbox for performing image processing tasks. Not only that, it provides “just enough” UI primitives to be able to quickly create a basic GUI for your program, including image display via multiple windows, buttons, and keyboard/mouse input. Furthermore, OpenCV seems to be plenty fast enough to do everything I need in real time, just with (accelerated where appropriate) CPU processing.

  So I went to work porting the ideas from the simple standalone Python/scikit tool. I thought of a refinement to the straight line detector– instead of just finding the longest straight edge, it creates a histogram of 360 rotation angles, and builds a list of lines corresponding to each angle. Then it sorts the angles by cumulative line length and allows the user to iterate through this list, which will hopefully provide the most likely straightened angle up front. Further, the tool allows making fine adjustments by 1/10 of an angle via the keyboard, not the mouse. It does all this while highlighting in red the straight line segments that are parallel to the horizontal axis, per the current candidate angle.

  
  
  

  The tool draws a light-colored grid over the frame to aid the user in visually verifying the straightness of the image. Further, the program has a mode that allows the user to see the algorithm’s detected edges :

  
  
  

  For the cropping phase, the program uses the Hough circle transform in a similar manner, finding the most likely circles (if the image to be processed is supposed to be a circle) and allowing the user to cycle among them while making precise adjustments via the keyboard, again, rather than the mouse.

  
  
  

  Running the Hough circle transform is a significantly more intensive operation than the line transform. When I ran it on a full 3300×3300 image, it ran for a long time. I didn’t let it run longer than a minute before forcibly ending the program. Is this approach unworkable ? Not quite– It turns out that the transform is just as effective when shrinking the image to 400×400, and completes in under 2 seconds on my Core i5 CPU.

  For rectangular cropping, I just settled on using OpenCV’s built-in region-of-interest (ROI) facility. I tried to intelligently find the best candidate rectangle and allow fine adjustments via the keyboard, but I wasn’t having much success, so I took a path of lesser resistance.

  Packaging and Residual Weirdness
  I realized that this tool would be more useful to a broader Windows-using base of digital preservationists if they didn’t have to install Python, establish a virtual environment, and install the prerequisite dependencies. Thus, I made the effort to figure out how to wrap the entire thing up into a monolithic Windows EXE binary. It is available from the project’s Github release page (another thing I figured out for the sake of this project !).

  The binary is pretty heavy, weighing in at a bit over 50 megabytes. You might advise using compression– it IS compressed ! Before I figured out the --onefile command for pyinstaller.exe, the generated dist/ subdirectory was 150 MB. Among other things, there’s a 30 MB FORTRAN BLAS library packaged in !

  Conclusion and Future Directions
  Once I got it all working with a simple tkinter UI up front in order to select between circle and rectangle crop modes, I unleashed the tool on 60 or so scans in bulk, using the Windows forfiles command (another learning experience). I didn’t put a clock on the effort, but it felt faster. Of course, I was livid with proudness the whole time because I was using my own tool. I just wish I had thought of it sooner. But, really, with 2100+ scans under my belt, I’m just getting started– I literally have thousands more artifacts to scan for preservation.

  The tool isn’t perfect, of course. Just tonight, I threw another scan at MobyCAIRO. Just go ahead and try to find straight lines in this specimen :

  
  
  

  I eventually had to use the text left and right of center to line up against the grid with the manual keyboard adjustments. Still, I’m impressed by how these computer vision algorithms can see patterns I can’t, highlighting lines I never would have guessed at.

  I’m eager to play with OpenCV some more, particularly the video processing functions, perhaps even some GPU-accelerated versions.

  The post Developing MobyCAIRO first appeared on Breaking Eggs And Making Omelettes.

• 10 Customer Segments Examples and Their Benefits

  9 mai 2024, par Erin

  Now that companies can segment buyers, the days of mass marketing are behind us. Customer segmentation offers various benefits for marketing, content creation, sales, analytics teams and more. Without customer segmentation, your personalised marketing efforts may fall flat. 

  According to the Twilio 2023 state of personalisation report, 69% of business leaders have increased their investment in personalisation. There’s a key reason for this — customer retention and loyalty directly benefit from personalisation. In fact, 62% of businesses have cited improved customer retention due to personalisation efforts. The numbers don’t lie. 

  Keep reading to learn how customer segments can help you fine-tune your personalised marketing campaigns. This article will give you a better understanding of customer segmentation and real-world customer segment examples. You’ll leave with the knowledge to empower your marketing strategies with effective customer segmentation. 

  What are customer segments ?

  Customer segments are distinct groups of people or organisations with similar characteristics, needs and behaviours. Like different species of plants in a garden, each customer segment has specific needs and care requirements. Customer segments are useful for tailoring personalised marketing campaigns for specific groups.

  Personalised marketing has been shown to have significant benefits — with 56% of consumers saying that a personalised experience would make them become repeat buyers. 

  Successful marketing teams typically focus on these types of customer segmentation :

  

  1. Geographic segmentation : groups buyers based on their physical location — country, city, region or climate — and language.
  2. Purchase history segmentation : categorises buyers based on their purchasing habits — how often they make purchases — and allows brands to distinguish between frequent, occasional and one-time buyers. 
  3. Product-based segmentation : groups buyers according to the products they prefer or end up purchasing. 
  4. Customer lifecycle segmentation : segments buyers based on where they are in the customer journey. Examples include new, repeat and lapsed buyers. This segmentation category is also useful for understanding the behaviour of loyal buyers and those at risk of churning. 
  5. Technographic segmentation : focuses on buyers’ technology preferences, including device type, browser type, and operating system. 
  6. Channel preference segmentation : helps us understand why buyers prefer to purchase via specific channels — whether online channels, physical stores or a combination of both. 
  7. Value-based segmentation : categorises buyers based on their average purchase value and sensitivity to pricing, for example. This type of segmentation can provide insights into the behaviours of price-conscious buyers and those willing to pay premium prices. 

  Customer segmentation vs. market segmentation

  Customer segmentation and market segmentation are related concepts, but they refer to different aspects of the segmentation process in marketing. 

  Market segmentation is the broader process of dividing the overall market into homogeneous groups. Market segmentation helps marketers identify different groups based on their characteristics or needs. These market segments make it easier for businesses to connect with new buyers by offering relevant products or new features. 

  On the other hand, customer segmentation is used to help you dig deep into the behaviour and preferences of your current customer base. Marketers use customer segmentation insights to create buyer personas. Buyer personas are essential for ensuring your personalised marketing efforts are relevant to the target audience. 

  10 customer segments examples

  Now that you better understand different customer segmentation categories, we’ll provide real-world examples of how customer segmentation can be applied. You’ll be able to draw a direct connection between the segmentation category or categories each example falls under.

  One thing to note is that you’ll want to consider privacy and compliance when you are considering collecting and analysing types of data such as gender, age, income level, profession or personal interests. Instead, you can focus on these privacy-friendly, ethical customer segmentation types :

  1. Geographic location (category : geographic segmentation)

  The North Face is an outdoor apparel and equipment company that relies on geographic segmentation to tailor its products toward buyers in specific regions and climates. 

  For instance, they’ll send targeted advertisements for insulated jackets and snow gear to buyers in colder climates. For folks in seasonal climates, The North Face may send personalised ads for snow gear in winter and ads for hiking or swimming gear in summer. 

  The North Face could also use geographic segmentation to determine buyers’ needs based on location. They can use this information to send targeted ads to specific customer segments during peak ski months to maximise profits.

  2. Preferred language (category : geographic segmentation)

  Your marketing approach will likely differ based on where your customers are and the language they speak. So, with that in mind, language may be another crucial variable you can introduce when identifying your target customers. 

  Language-based segmentation becomes even more important when one of your main business objectives is to expand into new markets and target international customers — especially now that global reach is made possible through digital channels. 

  Coca-Cola’s “Share a Coke” is a multi-national campaign with personalised cans and bottles featuring popular names from countries around the globe. It’s just one example of targeting customers based on language.

  3. Repeat users and loyal customers (category : customer lifecycle segmentation)

  Sephora, a large beauty supply company, is well-known for its Beauty Insider loyalty program. 

  It segments customers based on their purchase history and preferences and rewards their loyalty with gifts, discounts, exclusive offers and free samples. And since customers receive personalised product recommendations and other perks, it incentivises them to remain members of the Beauty Insider program — adding a boost to customer loyalty.

  By creating a memorable customer experience for this segment of their customer base, staying on top of beauty trends and listening to feedback, Sephora is able to keep buyers coming back.

  

  4. New customers (category : customer lifecycle segmentation)

  Subscription services use customer lifecycle segmentation to offer special promotions and trials for new customers. 

  HBO Max is a great example of a real company that excels at this strategy : 

  They offer 40% savings on an annual ad-free plan, which targets new customers who may be apprehensive about the added monthly cost of a recurring subscription.

  This marketing strategy prioritises fostering long-term customer relationships with new buyers to avoid high churn rates. 

  5. Cart abandonment (category : purchase history segmentation)

  With a rate of 85% among US-based mobile users, cart abandonment is a huge issue for ecommerce businesses. One way to deal with this is to segment inactive customers and cart abandoners — those who showed interest by adding products to their cart but haven’t converted yet — and send targeted emails to remind them about their abandoned carts.

  E-commerce companies like Ipsy, for example, track users who have added items to their cart but haven’t followed through on the purchase. The company’s messaging often contains incentives — like free shipping or a limited-time discount — to encourage passive users to return to their carts. 

  Research has found that cart abandonment emails with a coupon code have a high 44.37% average open rate. 

  6. Website activity (category : technographic segmentation)

  It’s also possible to segment customers based on website activity. Now, keep in mind that this is a relatively broad approach ; it covers every interaction that may occur while the customer is browsing your website. As such, it leaves room for many different types of segmentation. 

  For instance, you can segment your audience based on the pages they visited, the elements they interacted with — like CTAs and forms — how long they stayed on each page and whether they added products to their cart. 

  Matomo’s Event Tracking can provide additional context to each website visit and tell you more about the specific interactions that occur, making it particularly useful for segmenting customers based on how they spend their time on your website. 

  Try Matomo for Free

  Get the web insights you need, while respecting user privacy.

  Start for free

  No credit card required

  Amazon segments its customers based on browsing behaviour — recently viewed products and categories, among other things — which, in turn, allows them to improve the customer’s experience and drive sales.

  7. Traffic source (category : channel segmentation) 

  You can also segment your audience based on traffic sources. For example, you can determine if your website visitors arrived through Google and other search engines, email newsletters, social media platforms or referrals. 

  In other words, you’ll create specific audience segments based on the original source. Matomo’s Acquisition feature can provide insights into five different types of traffic sources — search engines, social media, external websites, direct traffic and campaigns — to help you understand how users enter your website.

  You may find that most visitors arrive at your website through social media ads or predominantly discover your brand through search engines. Either way, by learning where they’re coming from, you’ll be able to determine which conversion paths you should prioritise and optimise further. 

  8. Device type (category : technographic segmentation)

  Device type is customer segmentation based on the devices that potential customers may use to access your website and view your content. 

  It’s worth noting that, on a global level, most people (96%) use mobile devices — primarily smartphones — for internet access. So, there’s a high chance that most of your website visitors are coming from mobile devices, too. 

  However, it’s best not to assume anything. Matomo can detect the operating system and the type of device — desktop, mobile device, tablet, console or TV, for example. 

  By introducing the device type variable into your customer segmentation efforts, you’ll be able to determine if there’s a preference for mobile or desktop devices. In return, you’ll have a better idea of how to optimise your website — and whether you should consider developing an app to meet the needs of mobile users.

  Try Matomo for Free

  Get the web insights you need, while respecting user privacy.

  Start for free

  No credit card required

  9. Browser type (category : technographic segmentation)

  Besides devices, another type of segmentation that belongs to the technographic category and can provide valuable insights is browser-related. In this case, you’re tracking the internet browser your customers use. 

  Many browser types are available — including Google Chrome, Microsoft Edge, Safari, Firefox and Brave — and each may display your website and other content differently. 

  So, keeping track of your customers’ preferred choices is important. Otherwise, you won’t be able to fully understand their online experience — or ensure that these browsers are displaying your content properly. 

  

  10. Ecommerce activity (category : purchase history, value based, channel or product based segmentation) 

  Similar to website activity, looking at ecommerce activity can tell your sales teams more about which pages the customer has seen and how they have interacted with them. 

  With Matomo’s Ecommerce Tracking, you’ll be able to keep an eye on customers’ on-site behaviours, conversion rates, cart abandonment, purchased products and transaction data — including total revenue and average order value.

  Considering that the focus is on sales channels — such as your online store — this approach to customer segmentation can help you improve the sales experience and increase profitability. 

  Start implementing these customer segments examples

  With ever-evolving demographics and rapid technological advancements, customer segmentation is increasingly complex. The tips and real-world examples in this article break down and simplify customer segmentation so that you can adapt to your customer base. 

  Customer segmentation lays the groundwork for your personalised marketing campaigns to take off. By understanding your users better, you can effectively tailor each campaign to different segments. 

  If you’re ready to see how Matomo can elevate your personalised marketing campaigns, try it for free for 21 days. No credit card required.

  Try Matomo for Free

  21 day free trial. No credit card required.

  
  

  Your email address
  

  Your website address
  

  Your Analytics subdomain will be .matomo.cloud (change)

  Choose your analytics subdomain
  

  .matomo.cloud

  I accept the terms and conditions and data processing agreement (DPA)

  
  Your information will be used to create an account on our cloud service. For more information please consult our privacy policy.
  
  
  

  Start improving your websites now

  

• Revision 28933 : on bouge

  31 mai 2009, par ben.spip@… — Log

  on bouge